Geocarto International
ISSN: (Print) (Online) Journal homepage: https://www.tandfonline.com/loi/tgei20
Drivers of maize yield variability at household level
in Northern Ghana and Malawi
Stella Gachoki & Francis Muthoni
To cite this article: Stella Gachoki & Francis Muthoni (2023) Drivers of maize yield variability at
household level in Northern Ghana and Malawi, Geocarto International, 38:1, 2230948, DOI:
10.1080/10106049.2023.2230948
To link to this article:  https://doi.org/10.1080/10106049.2023.2230948
© 2023 The Author(s). Published by Informa
UK Limited, trading as Taylor & Francis
Group
Published online: 03 Jul 2023.
Submit your article to this journal 
Article views: 132
View related articles 
View Crossmark data
Full Terms & Conditions of access and use can be found at
https://www.tandfonline.com/action/journalInformation?journalCode=tgei20
GEOCARTO INTERNATIONAL
2023, VOL. 38, NO. 1, 2230948
https://doi.org/10.1080/10106049.2023.2230948
Drivers of maize yield variability at household level in
Northern Ghana and Malawi
Stella Gachoki and Francis Muthoni
International Institute of Tropical Agriculture (IITA), Arusha, Tanzania
ABSTRACT ARTICLE HISTORY
Maize is a staple food, but productivity has stagnated due to lim- Received 9 March 2023
ited access to advanced farming methods and knowledge. To pro- Accepted 23 June 2023
mote sustainable agriculture, understanding the factors affecting
maize yield at the farm level is crucial. This study used panel data KEYWORDS
on maize yield and agronomic practices in Northern Ghana and Satellite data; machine
learning; sustainable
Malawi from 2014 to 2020. Satellite-based environmental variables agriculture; yield predictions
were extracted at household locations, and Random Forest mod-
eling was used to identify factors influencing maize yield variabil-
ity. The models performance was sub-par with low R2 values
(
0.1 and 
0.24 for Northern Ghana and Malawi). Fertilizer and
precipitation were the most important factors explaining maize
yield variability. Spatial maps showed that Malawi’s maize yield
can increase with more fertilizer, but rainfall is essential. In
Northern Ghana, relying solely on fertilizer may not be enough to
boost maize production.
KEY POLICY HIGHLIGHTS
 Survey data on maize is limited in making accurate yield
predictions.
 Fertilizer use can increase maize yield in both Northern Ghana
and Malawi.
 Fertilizer use intervention strategies should be region-specific.
 The efficiency of fertilizer use is dependent on adequate rainfall
availability.
1. Introduction
Increased agricultural productivity is critical for Sub-Saharan Africa’s (SSA) economic
growth, poverty alleviation, and improved nutrition for the region’s growing population.
Maize (Zea mays L) is the second most cultivated and staple crop among SSA families,
and it is primarily grown by small-scale farmers (Oluoch et al. 2022). Maize yield variance
in SSA is influenced by agronomic, biophysical, and socio-economic factors such as var-
iety type, soil fertility, fertilizer application, intercropping, crop rotation, irrigation, farm
labour allocation, minimum tillage, input costs, and climatic shifts, among others
CONTACT Stella Gachoki gstellamuthoni@gmail.com

 2023 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group
This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/
licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is
properly cited. The terms on which this article has been published allow the posting of the Accepted Manuscript in a repository by
the author(s) or with their consent.
2 S. GACHOKI AND F. MUTHONI
(Danquah et al. 2020). However, the effect of these factors at the field level is lacking in
most SSA countries because maize yield data is typically aggregated to larger administra-
tive units, which averages out salient features of spatial and temporal variability in yield
data (Vergopolan et al. 2021). For example, even in farms with similar environmental
conditions, a farmer’s choice of maize cultivar, fertilizer, or pesticides can result in inter-
farm yield variability (Muthoni 2021). Therefore, characterizing the drivers of crop pro-
duction at the farm level is crucial for enabling evidence-based scaling out of sustainable
agronomic methods that boost maize productivity.
Globally, machine learning algorithms such as Random Forest (RF) have proven to be
more accurate in predicting and characterizing crop yield drivers because they can handle
large amounts of data and decode complex non-linear relationships between the response
variable and the predictor variables (Delerce et al. 2016). For example, Lohitha Reddy and
Siva Kumar (2023) employed three different machine learning techniques (decision tree
classifier, random forest classifier, and gradient boosting) to forecast crop yields using
weather and soil properties as predictor variables. Their study revealed that the random
forest classifier outperformed other algorithms in accurately predicting yield. Cai et al.
(2019) found that ML methods outperformed than Ordinary Least Square regression
when predicting wheat yield in Australia and also reported that combining climatic and
vegetation indices data improved prediction of wheat yield. Additionally, other studies
have utilized RF machine learning techniques to predict crop yield with high precision,
such as Charoen-Ung and Mittrapiyanuruk (2019) predicted sugarcane yield using RF
and forward feature selection, Jeong et al. (2016) forecasted the yields for maize, wheat,
and potato tubers, Everingham et al. (2016) predicted sugarcane yield in Tully, Australia,
and Ahmad et al. (2018) who predicted maize yield in Pakistan.
It is commonly assumed that machine learning methods like RF are immune to overfit-
ting. However, including skewed training samples, and irrelevant and redundant predictor
variables can significantly overfit the model when extrapolating beyond the areas where
the model was trained (Meyer et al. 2018, Meyer et al. 2019; Meyer and Pebesma 2021).
Furthermore, most data in nature are geographically dependent. Ignoring spatial depend-
encies in machine learning models might result in models that perform well on training
data but fall short on spatial predictions (Meyer et al. 2019). As a result, applying feature
selection approaches that incorporate target-oriented cross-validation (CV) processes,
such as Leave-Location-Out (LLO), is critical for improving the model’s performance
beyond the training area and preventing spatial overfitting (Meyer et al. 2019).
In this study, we used a panel household survey data on maize yield and agronomic
practices from Ghana and Malawi to 1) identify the target-oriented feature selection and
cross-validation strategies that improve the performance of the RF model for predicting
maize yield; 2) identify the most important sustainable agriculture intensification practices
and socio-economic factors that explain variance in maize yield; and 3) predict the spatial
distribution of maize yield under different management practices. The results of this
research will provide information on where to scale out specific bundles of sustainable
agriculture intensification (SAI) technologies with a low probability of failure.
2. Materials and methods
2.1. Study area
The study area covers two countries in SSA i.e. Ghana and Malawi (Figure 1). Maize is a
crucial crop in both countries, and its growth is heavily dependent on rainfall. Around
GEOCARTO INTERNATIONAL 3
Figure 1. Map of the study showing the location of the survey households and zones with relatively similar rainfall
patterns. The rainfall zones were generated from long-term (2014–2020) aggregation of annual TerraClimate satellite
rainfall estimates.
90% of smallholder farmers in Ghana and 97% in Malawi rely on maize farming as their
primary source of income (Msowoya et al. 2016; Scheiterle and Birner 2018; White 2019).
In Ghana, approximately 85% of maize production is consumed by humans, providing
about 30% of the combined calorie intake when combined with other cereals such as rice
and wheat, while the remaining 15% is used for animal feed to supplement poultry and
livestock production (Andam et al. 2017; Adu et al. 2021). In Malawi, maize makes up
more than half of the total calorie intake, with the central region having the largest har-
vested area, followed by the southern region (Warnatzsch et al. 2020). Soil infertility and
inadequate use of improved cultivars are the two major obstacles to maize productivity in
Ghana (Marfo-Ahenkora 2020), while in Malawi, the total family income and off-farm
employment are the major determinants of maize yield productivity (Tamene et al. 2016).
Climate variability has exacerbated maize productivity, resulting in malnutrition, poor
human development, and a higher poverty index among small-scale farmers who rely on
maize production for a living (Shi and Tao 2014; Parkes et al. 2018; Ngcamu and Chari
2020). As a result, determining the best agronomic strategies for increasing maize yield at
the farm level will allow these countries to make data-driven decisions to increase yield.
The Palmer Severity Drought Index (PDSI) is a reliable measure used to assess the
level of dryness or wetness in comparison to a historical average for a specific time
period. In our study we utilised the PDSI (Abatzoglou et al. 2018) to evaluate the weather
conditions for the two regions and seasons. We observed that the 2018–2019 growing sea-
son in Malawi was very wet while rainfall in all other seasons of both regions was below
the normal ranges with extreme droughts in Ghana during 2019 season (Figure 2).
4 S. GACHOKI AND F. MUTHONI
Figure 2. The average Palmer Drought Severity Index (PDSI) values for the growing seasons of Malawi and Ghana in
2013–2014 and 2018–2019. The growing season for Ghana spans from April to October, while for Malawi, it takes
place between October and April of the following year.
Table 1. Variables used in the models.
Class Continuous variables Categorical variables
Demographics Household size (Hhsize), age of the household head Female headed households (Femhead)
(Headage), the number of education years for the
household head (Headedu), maximum years of
adult education (Edumax), average years of adult
education (Meanedu) and plots fully managed by
female (FempltsF).
Production Area intercropped (intercropHa), fertilizer kg/ha Practice intercropping (Intercrop), applies
practices (FertHa), pesticide value/ha (PestHa), area under manure (Manure), uses hired labour
maize cultivation (MaizeA), land size (Landsize), (Labour), uses pesticides (Pest), any residue
number of plots owned (Nplots), livestock units left on farm (Residue), practices crop
(TLU), number of crops farmed (Ncrop), crop rotation (Rotation), can get credit (Credit),
diversity (CropD), livestock diversity (LvstD) and applies fertilizer (Fertilizer), practice
total income (Totincome). fallowing (Fallow), soil erosion (Erosion).
The text in brackets indicate how the variables are referred to in various figures.
2.2. Agronomic data
A panel household survey was conducted in Ghana and Malawi in 2013 and 2019 under
the Africa RISING program (https://africa-rising.net/; Tinonin et al. 2016). During the
two surveys, respondents provided information on household demographics and produc-
tion practices (Table 1).
2.3. Remote sensing variables
The gridded earth observation data were extracted using Google Earth Engine (GEE)
cloud computing platform (Gorelick et al. 2017). These variables include the vegetation
indices, meteorological, topography, socio-economic, hydrological, and soil properties
(Table 2). Vegetation indices and meteorological data were generated for each month dur-
ing the respective country’s maize growing season.
2.4. Model training and evaluation
Eliminating irrelevant and redundant predictor variables in machine learning models is
important because their inclusion can reduce the model’s performance. While many
GEOCARTO INTERNATIONAL 5
Table 2. Gridded environmental and weather data used in the model.
Original spatial
Variable name and reference resolution (m) Rationale/hypothesis
Vegetation indices Monthly Enhanced Vegetation Index (EVI 250 Vegetation indices are essential in agriculture as they assess plant health and
MODIS; janEVI, febEVI, marEVI, aprEVI, vigor. They are sensitive to changes in growth and development, which
julEVI, junEVI, augEVI, octEVI, novEVI, directly affect crop yield. Among the vegetation indices, EVI is particularly
decEVI - Didan 2015). The intext significant in predicting maize yield (Zhang et al. 2019; Meng et al. 2021)
annotations are;, because it can more accurately capture changes in vegetation in varying
atmospheric conditions and soil backgrounds.
Hydro-meteorological Monthly precipitation, soil moisture 4000 To support growth, maize roots need a proper amount of soil moisture to
(Soilm) and PDSI (pdsi) (TerraClimate absorb nutrients effectively. Low soil moisture levels can lead to drought
Abatzoglou et al. 2018). stress, causing reduced yields. Similarly, high soil moisture levels can also
be harmful, as it may lead to waterlogging and a decrease in oxygen
availability to the roots, resulting in lower yields. Hence, maintaining an
appropriate level of soil moisture is crucial for optimizing maize yield.
Topography Elevation (DEM - Farr et al. 2007). 30 Elevation has a significant impact on maize yield as it affects temperature and
rainfall levels. Generally, higher elevations have cooler temperatures that
can affect the rate of maize development and the length of the growing
season. Moreover, higher elevations usually receive more rainfall, which is
advantageous for maize growth and development, but excessive or
irregular rainfall can cause waterlogging or drought stress and lower the
maize yield.
Socio-economic Livestock density (LivDens) - (https:// 10000 Livestock can have both positive and negative impacts on maize yield. On the
www.fao.org/livestock-systems/global- one hand, their manure can provide essential nutrients that have been
distributions/en/). linked to increased maize productivity. However, when livestock density is
Access to markets (MarketAccess) - too high, it can result in competition for crop residue. In such cases, most
(Cattaneo et al. 2021). of the residue is consumed by the livestock, leaving only a small amount of
organic matter in the soil, which can lower soil nutrient levels and
ultimately reduce maize yield.
Soil properties Cation carbon exchange (CEC), organic 30 Soil structure, organic matter, and key soil nutrients like nitrogen, phosphorus,
carbon (OrgCab), soil ph (Soilph), soil and potassium are crucial for maize growth and yield. High levels of
bulk density (Soilbulk), clay, silt and organic matter improve soil structure, water-holding capacity, and fertility,
sand (iSDA - Hengl et al. 2021). leading to higher maize yields. Deficiencies in any of these nutrients can
reduce yield, emphasizing the importance of managing soil properties for
optimal maize production.
The text in brackets anotate how the variables are referred to in various figures.
6 S. GACHOKI AND F. MUTHONI
Figure 3. Boxplots showing the distribution of the maize yield data for Ghana and Malawi with (a) and without (b)
outliers were removed. The blue text is the number of households per cluster. The clusters are as described in
Figure 1.
feature elimination techniques are available, we used the VSURF feature elimination
method, which is included the VSURF package (Genuer et al. 2022) in the R program-
ming (R Core Team, 2020), to eliminate irrelevant or redundant variables. VSURF elimi-
nates feature in three processes i.e. thresholding, interpretation and predictive step. The
first step eliminates irrelevant variables from the dataset. The second step selects all varia-
bles related to the response for interpretation purpose. The third step refines the selection
by eliminating redundancy in the set of variables selected by the second step, for predic-
tion purpose. We focused on variables that were retained at the thresholding step, which
retains or drops variables based on how important they are in explain the response varia-
bles. Because most continuous household survey data lacked corresponding raster data,
we developed models that included all household survey data and those that only had cat-
egorical data to enable spatial predictions under various agronomic scenarios. To elabor-
ate, the categorical household survey data allowed these variables to be converted into
dummy variables, which could then be combined with the gridded raster data and toggled
on (1) or off (0) to visualize the impact of using or not using the respective agronomic
variable. What ‘appending dummy variables to gridded data’ does is create a grided layer
of zeros for each pixel (not using agronomic practices), and this layer can be turned on
by replacing all values with 1, indicating that all spaces use the agronomic variable. The
VSURF elimination method was applied to the two sets of the dataset (all predictors and
only categorical household survey data) independently. We used the ‘ranger’ method, as
implemented by the train function in the caret R package (Khun 2022), to train the maize
yield models and used the permutation method to rank the variable importance. Before
training the model, we used the CAST package to generate training and testing folds of
Leave-Location-Out (LLO) cross-validation. The LLO methodology internally subsets the
testing and training set and thus we did not withhold any data for independent testing of
the models. We then optimized the model by calculating the best mtry for each dataset
separately. The Root Mean Square Error (RMSE) and R-squared (R2) values were used to
GEOCARTO INTERNATIONAL 7
assess the model’s performance where higher R2 and lower RMSE values indicate a better
model performance. We employed the varmImp function in the caret package to deter-
mine and rank the significance of the variables. To gain insights into the relationship
between maize yield and the predictors, we generated partial dependence plots for the top
six predictors using the pdp R package (Greenwell 2022). These plots provide a visual rep-
resentation of the direction of the relationship between the response and the predictor
variable.
3. Results
3.1. Descriptive analysis
We investigated the distribution of maize yield for each season and country at different
rainfall clusters using box plots (Figure 3). To annotate the various datasets, we will refer
to Ghana data as D1 and D2 for the 2013 and 2019 surveys, respectively, and Malawi
data as D3 and D4 for the 2013 and 2019 surveys, respectively.
To better understand the distribution of maize yield data based on all the predictor
variables, we created histograms (Appendix 1) for various continuous variables for each
country and season individually. The total number of predictor variables for D1 and D3
was 43, while D2 had 56 predictors and D4 had 57 predictors.
3.2. Feature elimination
The count of predictor variables that remained after elimination is presented in Table 3.
Additional information on the actual names of the predictors that were retained can be
found in the supplementary information (SS1).
3.3. Model performances, variable importance, partial dependence plots and spatial
predictions
The models only explained a small variability in maize yield with low R2 values across all
seasons for each country (Table 4). When continuous household data were used, the
explained variability was greater (11–15% in Northern Ghana and 24–35% in Malawi)
than when only categorical data were used (6–10% in Northern Ghana and 7–14% in
Table 3. The number of retained predictor variables after the VSURF thresholding step.
Model D1 D2 D3 D4
All predictors 49 51 52 52
Categorical HHþ satellite data 37 39 39 42
Table 4. Model performance metrics when all predictors were used and when only the categorical household survey
was used.
Ghana Malawi
All Categorical All Categorical
D1 D2 D3 D4
l¼ 712.28 D2 D1 l¼ 820.43 l¼ 1663.03 D4 D3 l¼ 1210.15
RMSE 415.88 407.20 426.89 418.72 906.48 635.99 1038.53 703.88
nRMSE 0.58 0.57 0.52 0.51 0.54 0.52 0.62 0.58
R2 0.11 0.15 0.06 0.10 0.35 0.24 0.14 0.07
8 S. GACHOKI AND F. MUTHONI
Figure 4. Variable importance and partial dependence plots for Ghana in 2013. (a) and (b) All predictor and categor-
ical variables importance plots respectively. (c) and (d) Partial dependence plots for the top 6 predictors with all pre-
dictors and only with categorical variables respectively.
MalawiThis implies that the quantity of measurable agronomic practices used explains
yield variability better than whether or not that agronomic variable is used. For both
countries and seasons, the RMSE values obtained were consistently high, with normalized
RMSE values (nRMSE; RMSE/mean yield) exceeding 50%. These values suggest that the
model predictions were either overestimating or underestimating the actual yield by a sig-
nificant margin, often by as much as twice or half the true value. The results underscore
the necessity of refining the predictive model to enhance its accuracy and practical
applicability.
Previous studies have reported the usefulness of fertilizer application in increasing
maize yield in Northern Ghana (Braimoh and Vlek 2006; Kanton et al. 2016; Buah et al.
2017). Our analysis identified the amount of fertilizer used per hectare and total income
(Figure 4a) as the most significant agronomic practices that positively (Figure 4c) influ-
enced maize yield in Ghana in 2013. Interestingly, when considering only the categorical
version of the agronomic practices, the importance of these two variables was relatively
low (Figure 4b), indicating that the quantity used mattered more than simply their pres-
ence or absence. Both datasets showed that the total amount of rainfall experienced in
October - which marks the end of the season - had a positive influence on maize yield
(Figure 4c and d). Agronomic practices were found to be poorly correlated with maize
yield variability in 2019 (Figure 5a and b). Instead, the most significant factors influencing
yield productivity were August precipitation, which had a positive effect, and temperature,
which had a negative impact (Figure 5c and d). The observed dynamics may be attributed
to the exceptionally dry season (Figure 2), which resulted in reduced soil moisture and
likely exacerbated the effects of temperature on yield.
The spatial prediction maps indicated that introducing fertilizer as an agronomic prac-
tice resulted in minimal improvements in maize yield in both seasons (Figure 6a and b).
The yield gain observed was relatively low (<50kg/ha) but parts of the upper west and
northern region had higher yield gain of more than 50 kg/ha (Figure 6c). The limited
yield gain observed may be attributed to two key factors: first, the relatively dry
GEOCARTO INTERNATIONAL 9
Figure 5. Variable importance and partial dependence plots for Ghana in 2019. (a) and (b) All predictor and categor-
ical variables importance plots respectively. (c) and (d) Partial dependence plots for the top 6 predictors with all pre-
dictors and only with categorical variables respectively.
conditions during the two seasons (Figure 2); and second, the low ranking of fertilizer use
(yes/no) as a significant predictor of yield.
While recent studies have found a limited yield response to fertilizer use in Malawi
(Burke et al. 2022; De Weerdt and Duchoslav 2022), several other studies have demon-
strated that applying fertilizer and improving access to it can significantly boost maize
yield productivity (Sauer and Tchale 2009; Wang et al. 2019; Burke and Jayne 2021;
Cairns et al. 2021; Cassim and Pemba 2022). According to the 2013 season analysis, fertil-
izer usage per hectare and the extent of land devoted to maize cultivation were the pri-
mary factors accounting for yield variability (Figure 7a), with the former exerting a
positive effect and the latter having a negative impact. respectively (Figure 7c). Although
soil moisture was identified as the most critical variable affecting maize yield when cat-
egorical agronomic practices were employed for predictions (Figure 7b), the observation
that yield declined with increasing soil moisture (Figure 7d) during a relatively dry season
(Figure 2) is perplexing. Fertilizer use (both quantity and yes/no) was an important factor
in 2019 (Figure 8a and b) with a positive effect on maize yield (Figure 8c and d). Total
household income and labor were significant factors as continuous variables this season,
but labor was less important in categorical analysis (Figure 8a and b). Livestock density
had the most significant positive impact in categorical analysis, likely due to manure use
and its positive effect on maize yield (Wang et al. 2019).
Spatial predictions based on agronomic models demonstrated that the introduction of
fertilizer in the 2019 growing season resulted in a significantly greater increase in maize
yield as compared to the 2013 season (Figure 9). This outcome may be attributed to the
favorable soil moisture conditions in 2019 (Figure 2), which allowed for enhanced fertil-
izer uptake by crops and ultimately contributed to improved yield. Even so, it is impor-
tant to note that the average maize yield was higher in 2013 as compared to 2019. Two
possible reasons could explain this phenomenon: Firstly, the prevalence of extreme floods
and soil erosion in Malawi (McCarthy et al. 2021) may have reduced crop yield,
10 S. GACHOKI AND F. MUTHONI
Figure 6. The spatial maize yield prediction and yield gain for Ghana in 2013 and 2019 when fertilizer use was incor-
porated as a useful agronomic practice. (a) When no agronomic practice was used. (b) Fertilizer use and (c) yield
gain/loss (Figure 6b – Figure 6a).
particularly given the excessively wet weather in 2019. Secondly, excessively moist envi-
ronments can increase the incidence of corn ear infections (Wang et al. 2019), thereby
leading to a decline in yield.
4. Discussion
This study examined the factors that affect the maize yield in different regions and peri-
ods in northern Ghana and Malawi. To do this, we looked at various biophysical, socio-
GEOCARTO INTERNATIONAL 11
Figure 7. Variable importance and partial dependence plots for Malawi in 2013. (a) and (b) All predictor and categor-
ical variables importance plots respectively. (c) and (d) Partial dependence plots for the top 6 predictors with all pre-
dictors and only with categorical variables respectively.
Figure 8. Variable importance and partial dependence plots for Malawi in 2019. (a) and (b) All predictor and categor-
ical variables importance plots respectively. (c) and (d) Partial dependence plots for the top 6 predictors with all pre-
dictors and only with categorical variables respectively.
economic and farm management practices as potential predictors and used a random for-
est machine learning algorithm with spatial blocking cross-validation. Despite efforts to
develop accurate models, the performance was suboptimal, with explained variability
ranging from 6 to 15% in Ghana and between 7 to 35% in Malawi over the course of two
seasons (Table 4). While it is true that spatial blocking cross-validation can lead to
12 S. GACHOKI AND F. MUTHONI
Figure 9. The spatial maize yield prediction and yield gain for Malawi in 2013 and 2019 when fertilizer use was incor-
porated as a useful agronomic practice. (a) When no agronomic practice was used. (b) Fertilizer use and (c) yield
gain/loss (Figure 9b – Figure 9a).
reduced R2 values (Meyer et al. 2018; Meyer et al. 2019; Meyer and Pebesma 2021), there
may be other factors that may have contributed to the underperformance of the models.
For example, farmers reported yields from a different number of plots that were spatially
displaced. These imprecise locations of farmer plots could have introduced errors when
matching with remote sensing variables (Burke and Lobell 2017; Lobell et al. 2020). This
can be resolved by aggregating the yield data into larger administrative zones although
the practice can mask details in heterogeneous farms. Alternatively, we recommend that
household surveys should endeavour to precisely map the plot boundaries to enable
matching with satellite data. Also, the maize yield data was based on self-reported esti-
mates and numerous studies have shown that self-reported estimates are frequently
inaccurate when compared to farm-level estimates derived from actual harvest measure-
ments (Jin et al. 2017; Scheiterle et al. 2019; Burke et al. 2020; Li et al. 2022).
The low spatial resolution of the predictor variables used in the models, which were
resampled from about 4 to 0.03 km, could also be a contributing factor to the poor per-
formance of the models. Generating reliable satellite-based productivity estimates for
smallholder farms in sub-Saharan Africa, which are typically characterized by small land
size and intercropping, is unlikely when using low spatial resolution data due to the pres-
ence of mixed crops within a single pixel (Jin et al. 2017; Li et al. 2022). Studies have
demonstrated that utilizing higher spatial resolution satellite data, such as those provided
by the Sentinel-2 mission (10m) and PlanetScope (3m), has resulted in improved model
performance (R2>0.5; Li et al. 2022). However, the utility of such high-resolution data is
limited by frequent cloud cover and requires significant computational resources, particu-
larly when analyzing vast areas. Furthermore, the choice of satellite-based predictor varia-
bles used in this study may have been insufficient in explaining the variations in maize
yield. According to Jin et al. (2017) and Burke and Lobell (2017) Green Chlorophyll
Vegetation Index (GCVI) is more effective at predicting maize yield than other vegetation
indices, likely due to its ability to capture nutrient deficiency, which is highly correlated
GEOCARTO INTERNATIONAL 13
with yield. In addition, factors such as Leaf Area Index (LAI), radiation, and sowing
period have been identified as good predictors of maize yield in several studies (Srivastava
et al. 2017; Lambert et al. 2018; Danquah et al. 2020; Li et al. 2022).
Maize farming in the sub-Saharan Africa region heavily relies on adequate rainfall, which
may explain why precipitation and soil moisture emerged as significant factors in explaining
the variability of maize yield. Both Malawi and Ghana have made significant investments in
fertilizer subsidy programs as part of their efforts to increase maize productivity (Mapila
et al. 2012; Fearon et al. 2015; Ragasa and Chapoto 2017; Scheiterle and Birner 2018;
Andani et al. 2020; Cassim and Pemba 2022; De Weerdt and Duchoslav 2022). There is a
debate on the usefulness of fertilizer subsidy programs, with some studies reporting low
yield response (Benin et al. 2013; Fearon et al. 2015; Andani et al. 2020; Burke et al. 2022),
while others suggest that these programs have led to improved maize productivity by mak-
ing fertilizers more accessible and increasing their usage (Braimoh and Vlek 2006;
Chibwana et al. 2014; Kanton et al. 2016; Buah et al. 2017; Wang et al. 2019). Our results
suggest that the application of fertilizer can significantly enhance maize production in both
Malawi and Ghana during seasons with adequate soil moisture. This could be attributed to
the fact that both countries face challenges of low soil fertility caused by a combination of
factors such as low nutrient levels, continuous cropping, overgrazing, deforestation, and
poor soil and water management practices (Tittonell and Giller 2013; Vuntade et al. 2022).
In terms of yield gain/loss, Malawi saw the highest increase in maize yield (Figure 9)
when fertilizers were used, while Ghana experienced a much smaller increase (Figure 6).
The high yield gain in Malawi could be because several studies have linked the use of fer-
tilizer, urea, and manure to high maize yield (Snapp et al. 2014; Tamene et al. 2016; Liu
and Basso 2017; Wang et al. 2019), as well as intercropping, which acts as a soil fertility
replenishment (Akinnifesi et al. 2006; Silberg et al. 2017). The difference in yield gain
between Ghana and Malawi in 2019 may be attributed to Ghana’s comparatively dry sea-
son and Malawi’s comparatively wet season, which likely explains why Ghana’s yield
increase was low (<50 kg/ha) while Malawi’s was high (> 400 kg/ha). Another possible
reason why the Ghana season had a lower yield increase could be the limited access to
modern agricultural practices, such as mechanization and the use of improved seed vari-
eties, which continue to constrain productivity (Ragasa and Chapoto 2017).
The presence of parasitic weeds like Striga (Scheiterle et al. 2019; Adu et al. 2022;
Martey et al. 2022) and pests like fall armyworm (Agboyi et al. 2020; Nagoshi et al.
2021; Yeboah et al. 2021) outbreaks in maize farms and increased cost of pesticide that
hinders their control could also be a contributing factor to why fertilizer use does not
necessarily result in increased yields. Although hand-picking of the striga weed is a
commonly used method, it is not sustainable in the long term (Kabambe et al. 2008;
Wang et al. 2019). Therefore, an integrated approach that incorporates different control
methods is necessary to effectively manage the weed. Push-Pull technology, which
involves planting desmodium and bracharia grass, has been shown to effectively reduce
striga weed infestation and ultimately increase maize yield, offering a sustainable and
integrated approach to weed control (Niassy et al. 2022). To potentially enhance maize
yield productivity, factors such as timely fertilizer application, adjusting planting dates
to accommodate climate variability (Fosu-Mensah et al. 2019; Warnatzsch and Reay
2020), educating farmers on the appropriate fertilizer amounts (Addai and Owusu 2014;
Asante et al. 2019; Wang et al. 2019; Andani et al. 2020; Cairns et al. 2021; Setsoafia
et al. 2022), and promoting the adoption of improved seed varieties may also be
beneficial.
14 S. GACHOKI AND F. MUTHONI
Despite the poor performance of the models in this study, we have identified impor-
tant variables that are consistent with existing knowledge and previous studies on maize
yield. To enhance the model performance, we recommend the following: 1) include
satellite-based factors like GCVI and LAI, which have shown better performance in
predicting yield; 2) integrate a crop classification map that distinguishes maize and non-
maize fields; 3) refine yield data using simple thresholds and generate categorical
predictive maps rather than actual yield; and 4) explore simple regression models that
directly correlate yield data with vegetation indices, as these have been found to better
explain variations in maize yield in sub-Saharan African countries (Jin et al. 2017; Li
et al. 2022).
5. Conclusion
The identification of maize yield determinants through the use of household survey data
and low spatial resolution satellite-based estimates of the environment has produced a
model that performs moderately. Nonetheless, the significant variables identified align
with existing knowledge of the factors that affect maize yield variability both at the farm
and larger administrative levels. The findings of this study suggest that promoting the use
of fertilizers is a viable option for improving maize yield in Ghana and Malawi.
Additionally, since precipitation plays a crucial role in determining yield, it is recom-
mended that measures such as rainwater harvesting be promoted to help cushion against
the impact of extreme dry seasons.
Acknowledgements
This study was partly funded by USAID through grant number: AID-BFS-G-11-00002 under the Feed the
Future initiative to support Africa RISING program. We would like to thank all funders who support the
Sustainable Intensification of Mixed Farming Systems Initiative through their contributions to the CGIAR
Trust Fund. The authors further acknowledge funding from Bill and Melinda Gates Foundation (BMGF)
for grant number INV-005431 in support of Excellence in Agronomy Initiative.
Disclosure statement
Authors declare no conflict of interest.
Data availability statement
All the R programming scripts and excel files used in fitting the models are available in github repository
(https://github.com/Muthono19/Predicting-Maize-Yield-in-Ghana-and-Malawi.git). The remote sensing
data used is open source and can be downloaded through GEE.
References
Abatzoglou JT, Dobrowski SZ, Parks SA, Hegewisch KC. 2018. TerraClimate, a high-resolution global
dataset of monthly climate and climatic water balance from 1958–2015. Sci Data. 5(1):1–12. doi: 10.
1038/sdata.2017.191.
Addai KN, Owusu V. 2014. Technical efficiency of maize farmers across various agro ecological zones of
Ghana. J Agric Environ Sci. 3(1):2334–2412.
Adu GB, Badu-Apraku B, Akromah R, Amegbor IK, Adogoba DS, Haruna A, Manigben KA, Aboyadana
PA, Wiredu AN. 2021. Trait profile of maize varieties preferred by farmers and value chain actors in
northern Ghana. Agron Sustain Dev. 41(4):50. doi: 10.1007/s13593-021-00708-w.
GEOCARTO INTERNATIONAL 15
Adu GB, Badu-Apraku B, Akromah R, Awuku FJ. 2022. Combining abilities and heterotic patterns among
early maturing maize inbred lines under optimal and striga-infested environments. Genes. 13(12):2289.
doi: 10.3390/GENES13122289/S1.
Agboyi LK, Goergen G, Beseh P, Mensah SA, Clottey VA, Glikpo R, Buddie A, Caf
a G, Offord L, Day R,
et al. 2020. Parasitoid complex of fall armyworm, Spodoptera frugiperda, in Ghana and Benin. Insects.
11(2):68. doi: 10.3390/insects11020068.
Ahmad I, Saeed U, Fahad M, Ullah A, Habib Ur Rahman M, Ahmad A, Judge J. 2018. Yield forecasting
of spring maize using remote sensing and crop modeling in Faisalabad-Punjab Pakistan. J Indian Soc
Remote Sens. 46(10):1701–1711. doi: 10.1007/S12524-018-0825-8/METRICS.
Akinnifesi FK, Makumba W, Kwesiga FR. 2006. Sustainable maize production using gliricidia/maize inter-
cropping in southern Malawi. Ex Agric. 42(4):441–457. doi: 10.1017/S0014479706003814.
Andam K, Johnson M, Ragasa C, Kufoalor D, Das Gupta S. 2017. A Chicken and Maize Situation: the
Poultry Feed Sector in Ghana, AgriSciRN: Agribusiness (Topic).
Andani A, Moro A-HB, Issahaku G. 2020. Fertilizer subsidy policy and smallholder farmers’ crop prod-
uctivity: the case of maize production in North-Eastern Ghana. J Agric Extens Rural Dev. 12(2):18–25.
doi: 10.5897/JAERD2020.1138.
Asante BO, Temoso O, Addai KN, Villano RA. 2019. Evaluating productivity gaps in maize production
across different agroecological zones in Ghana. Agric Syst. 176:102650. 102650. doi: 10.1016/j.agsy.
2019.102650.
Benin S, Johnson M, Abokyi E, Ahorbo G, Jimah K, Nasser G, Owusu V, Taabazuing J, Tenga A. 2013.
Revisiting agricultural input and farm support subsidies in Africa: the case of Ghana’s mechanization,
fertilizer, block farms, and marketing programs. SSRN J. doi: 10.2139/ssrn.2373185.
Braimoh AK, Vlek PLG. 2006. Soil quality and other factors influencing maize yield in northern Ghana.
Soil Use Manage. 22(2):165–171. doi: 10.1111/j.1475-2743.2006.00032.x.
Buah SSJ, Ibrahim H, Derigubah M, Kuzie M, Segtaa JV, Bayala J, Zougmore R, Ouedraogo M.,. 2017.
Tillage and fertilizer effect on maize and soybean yields in the Guinea savanna zone of Ghana. Agric
Food Secur. 6(1):1–11. doi: 10.1186/S40066-017-0094-8/TABLES/5.
Burke M, Lobell DB. 2017. Satellite-based assessment of yield variation and its determinants in small-
holder African systems. Proc Natl Acad Sci U S A. 114(9):2189–2194. doi: 10.1073/PNAS.1616919114/
SUPPL_FILE/PNAS.201616919SI.PDF.
Burke WJ, Jayne TS. 2021. Disparate access to quality land and fertilizers explain Malawi’s gender yield
gap. Food Policy. 100:102002. doi: 10.1016/j.foodpol.2020.102002.
Burke WJ, Jayne TS, Snapp SS. 2022. Nitrogen efficiency by soil quality and management regimes on
Malawi farms: can fertilizer use remain profitable? World Dev. 152:105792. doi: 10.1016/j.worlddev.
2021.105792.
Burke WJ, Snapp SS, Jayne TS. 2020. An in-depth examination of maize yield response to fertilizer in
Central Malawi reveals low profits and too many weeds. Agric Econ. 51(6):923–940. doi: 10.1111/agec.
12601.
Cai Y, Guan K, Lobell D, Potgieter AB, Wang S, Peng J, Xu T, Asseng S, Zhang Y, You L, et al. 2019.
Integrating satellite and climate data to predict wheat yield in Australia using machine learning
approaches. Agric For Meteorol. 274:144–159. doi: 10.1016/j.agrformet.2019.03.010.
Cairns JE, Chamberlin J, Rutsaert P, Voss RC, Ndhlela T, Magorokosho C.,. 2021. Challenges for sustain-
able maize production of smallholder farmers in sub-Saharan Africa. J Cereal Sci. 101:103274. doi: 10.
1016/j.jcs.2021.103274.
Cassim L, Pemba LA. 2022. The interactive effects of farm input subsidy program and agricultural exten-
sion eervices on smallholder maize production and Technical Efficiency in Malawi. Malawi J Econ.
2(1):66–84. Available at: https://www.ajol.info/index.php/mje/article/view/228064. (Accessed: 8 March
2023).
Cattaneo A, Nelson A, McMenomy T. 2021. Global mapping of urban-rural catchment areas reveals
unequal access to services. Proc Natl Acad Sci USA. 118(2):e2011990118. doi: 10.1073/PNAS.
2011990118/SUPPL_FILE/PNAS.2011990118.SD01.XLSX.
Charoen-Ung P, Mittrapiyanuruk P. 2019. Sugarcane yield grade prediction using random forest with for-
ward feature selection and hyper-parameter tuning. Adv Intell Syst Comput. 769:33–42. doi: 10.1007/
978-3-319-93692-5_4/COVER.
Chibwana C, et al. 2014. Measuring the impacts of Malawi’s farm input subsidy programme. Afr J Agric
Resour Econ. 9(2):132–147. doi: 10.22004/AG.ECON.176511.
Danquah EO, et al. 2020. Monitoring and modelling analysis of maize of maize (Zea mays L) yield gap in
smallholder farming in Ghana. Agriculture. 10(9):420. doi: 10.3390/AGRICULTURE10090420.
16 S. GACHOKI AND F. MUTHONI
Delerce S, Dorado H, Grillon A, Rebolledo MC, Prager SD, Patin~o VH, Garces Varon G, Jimenez D.
2016. Assessing weather-yield relationships in rice at local scale using data mining approaches. PLoS
One. 11(8):e0161620. doi: 10.1371/JOURNAL.PONE.0161620.
Didan K. 2015. MOD13Q1 MODIS/Terra vegetation indices 16-day L3 global 250m SIN Grid V006
[Dataset]. NASA EOSDIS Land Processes DAAC. accessed 2023-02-22 from doi: 10.5067/MODIS/
MOD13Q1.006.
Everingham Y, Sexton J, Skocaj D, Inman-Bamber G. 2016. Accurate prediction of sugarcane yield using a
random forest algorithm. Agron Sustain Dev. 36(2):1–9. doi: 10.1007/S13593-016-0364-Z/FIGURES/3.
Farr TG, Rosen PA, Caro E, Crippen R, Duren R, Hensley S, Kobrick M, Paller M, Rodriguez E, Roth L,
et al. 2007. The shuttle radar topography mission. Rev Geophys. 45(2):2004. doi: 10.1029/
2005RG000183.
Fearon J, Adraki PK, Boateng VF. 2015. ‘Fertilizer subsidy programme in Ghana: evidence of performance
after six years of implementation’. 5(21). Available at: www.iiste.org. (Accessed: 8 March 2023).
Fosu-Mensah BY, Manchadi A, Vlek PLG. 2019. Impacts of climate change and climate variability on
maize yield under rainfed conditions in the sub-humid zone of Ghana: a scenario analysis using
APSIM. West Afr J Appl Ecol. 27(1):108–126. doi: 10.4314/wajae.v27i1.
Genuer, R, Jean-Michel, P, Christine, TM, Variable selection using random forests (VSURF), CRAN
Repos, 2022
Gorelick N, Hancher M, Dixon M, Ilyushchenko S, Thau D, Moore R.,. 2017. Google Earth Engine:
planetary-scale geospatial analysis for everyone. Remote Sens Environ. 202:18–27. doi: 10.1016/j.rse.
2017.06.031.
Greenwell B. 2022. Package ’pdp’- Partial Dependence Plots. Available at: https://cran.r-project.org/web/
packages/pdp/pdp.pdf. (Accessed: 10 February 2023).
Hengl T, Miller MAE, Krizan J, Shepherd KD, Sila A, Kilibarda M, Antonijevic O, Glusica L, Dobermann
A, Haefele SM, et al. 2021. African soil properties and nutrients mapped at 30 m spatial resolution
using two-scale ensemble machine learning. Sci Rep. 11(1):1–18. doi: 10.1038/s41598-021-85639-y.
Jeong JH, Resop JP, Mueller ND, Fleisher DH, Yun K, Butler EE, Timlin DJ, Shim K-M, Gerber JS,
Reddy VR, et al. 2016. Random forests for global and regional crop yield predictions. PLoS One. 11(6):
e0156571. doi: 10.1371/JOURNAL.PONE.0156571.
Jin Z, Azzari G, Burke M, Aston S, Lobell D.,. 2017. Mapping smallholder yield heterogeneity at multiple
scales in Eastern Africa. Remote Sens. 9(9):931. doi: 10.3390/rs9090931.
Kabambe VH, Katunga LA, Kapewa T. 2008. Screening legumes for integrated management of witchweeds
(Alectra vogelii and Striga asiatica) in Malawi. Afr J Agric Res. 3:708–715.
Kanton RAL, Prasad PVV, Mohammed AM, Bidzakin JK, Ansoba EY, Asungre PA, Lamini S, Mahama
G, Kusi F, Sugri I, et al. 2016. Organic and inorganic fertilizer effects on the growth and yield of maize
in a dry agro-ecology in Northern Ghana. J Crop Improve. 30(1):1–16. doi: 10.1080/15427528.2015.
1085939.
Khun M. 2022. Classification and regression training: package caret. Available at: https://cran.r-project.org/
web/packages/caret/caret.pdf. (Accessed: 26 January 2023).
Lambert M-J, Traore PCS, Blaes X, Baret P, Defourny P. 2018. Estimating smallholder crops production
at village level from Sentinel-2 time series in Mali’s cotton belt. Remote Sens Environ. 216:647–657.
doi: 10.1016/j.rse.2018.06.036.
Li C, Chimimba EG, Kambombe O, Brown LA, Chibarabada TP, Lu Y, Anghileri D, Ngongondo C,
Sheffield J, Dash J, et al. 2022. Maize yield estimation in intercropped smallholder fields using satellite
data in Southern Malawi. Remote Sens. 14(10):2458. doi: 10.3390/rs14102458.
Liu L, Basso B. 2017. Spatial evaluation of maize yield in Malawi. Agric Syst. 157:185–192. doi: 10.1016/j.
agsy.2017.07.014.
Lobell DB, Azzari G, Burke M, Gourlay S, Jin Z, Kilic T, Murray S. 2020. Eyes in the sky, boots on the
ground: assessing satellite- and ground-based approaches to crop yield measurement and analysis. Am
J Agric Econ. 102(1):202–219. doi: 10.1093/ajae/aaz051.
Lohitha Reddy K, Siva Kumar AP. 2023. Machine learning techniques for weather based crop yield pre-
diction. 2023 Third International Conference on Artificial Intelligence and Smart Energy (ICAIS). pp.
1263–1268. doi: 10.1109/ICAIS56108.2023.10073740.
Mapila MATJ, Njuki J, Delve RJ, Zingore S, Matibini J. 2012. Determinants of fertiliser use by smallholder
maize farmers in the Chinyanja Triangle in Malawi, Mozambique and Zambia. Agric Econ Res Policy
Pract Southern Afr. 51(1):21–41. doi: 10.1080/03031853.2012.649534.
Marfo-Ahenkora E. 2020. Strategies for sustainable productivity of maize (Zea mays L.) - based farming
systems of smallholder farmers in Ghana. University of Cape Coast. Available at: http://ir.ucc.edu.gh/
jspui/handle/123456789/7197. (Accessed: 28 February 2023).
GEOCARTO INTERNATIONAL 17
Martey E, Etwire PM, Wossen T, Menkir A, Abdoulaye T. 2022. Impact assessment of Striga resistant
maize varieties and fertilizer use in Ghana: a panel analysis. Food Energy Secur. 12(2):e432. doi: 10.
1002/fes3.432.
McCarthy N, Kilic T, Brubaker J, Murray S, de la Fuente A. 2021. Droughts and floods in Malawi:
impacts on crop production and the performance of sustainable land management practices under wea-
ther extremes. Environ Dev Econ. 26(5-6):432–449. doi: 10.1017/S1355770X20000455.
Meng L, Liu H, Ustin SL, Zhang X. 2021. Predicting maize yield at the plot scale of different fertilizer sys-
tems by multi-source data and machine learning methods. Remote Sens. 13(18):3760. doi: 10.3390/
rs13183760.
Meyer H, Reudenbach C, Hengl T, Katurji M, Nauss T. 2018. Improving performance of spatio-temporal
machine learning models using forward feature selection and target-oriented validation. Environ Model
Softw. 101:1–9. doi: 10.1016/j.envsoft.2017.12.001.
Meyer H, Reudenbach C, Wo€llauer S, Nauss T. 2019. Importance of spatial predictor variable selection in
machine learning applications – moving from data reproduction to spatial prediction. Ecol Modell.
411:108815. doi: 10.1016/j.ecolmodel.2019.108815.
Meyer H, Pebesma E. 2021. Predicting into unknown space? Estimating the area of applicability of spatial
prediction models. Methods Ecol Evol. 12(9):1620–1633. doi: 10.1111/2041-210X.13650.
Msowoya K, Madani K, Davtalab R, Mirchi A, Lund JR. 2016. Climate change impacts on maize produc-
tion in the warm heart of Africa. Water Resour Manage. 30(14):5299–5312. doi: 10.1007/S11269-016-
1487-3/FIGURES/8.
Muthoni F. 2021. Machine learning model accurately predict maize grain yields in conservation agricul-
ture systems in Southern Africa. 2021 9th International Conference on Agro-Geoinformatics, Agro-
Geoinformatics 2021. doi: 10.1109/AGRO-GEOINFORMATICS50104.2021.9530335.
Nagoshi RN, Koffi D, Agboka K, Adjevi AKM, Meagher RL, Goergen G.,. 2021. The fall armyworm strain
associated with most rice, millet, and pasture infestations in the Western Hemisphere is rare or absent
in Ghana and Togo. PLoS One. 16(6):e0253528. doi: 10.1371/JOURNAL.PONE.0253528.
Ngcamu BS, Chari F. 2020. Drought influences on food insecurity in Africa: a systematic literature review.
IJERPH. 17(16):5897. doi: 10.3390/ijerph17165897.
Niassy S, Agbodzavu MK, Mudereri BT, Kamalongo D, Ligowe I, Hailu G, Kimathi E, Jere Z, Ochatum
N, Pittchar J, et al. 2022. Performance of push-pull technology in low-fertility soils under conventional
and conservation agriculture farming systems in Malawi. Sustainability. 14(4):2162. doi: 10.3390/
su14042162.
Oluoch KO, De Groote H, Gitonga ZM, Jin Z, Davis KF. 2022. A suite of agronomic factors can offset
the effects of climate variability on rainfed maize production in Kenya. Sci Rep. 12(1):1–8. doi: 10.
1038/s41598-022-19286-2.
Parkes B, Sultan B, Ciais P. 2018. The impact of future climate change and potential adaptation methods
on Maize yields in West Africa. Clim Change. 151(2):205–217. doi: 10.1007/S10584-018-2290-3/
METRICS.
R Core, Team, R: A language and environment for statistical computing [Internet], 2020, http://www.r-
project.org/index.html (Accessed: 21 August 2020).
Ragasa C, Chapoto A. 2017. Moving in the right direction? The role of price subsidies in fertilizer use
and maize productivity in Ghana. Food Sec. 9(2):329–353. doi: 10.1007/S12571-017-0661-7/METRICS.
Sauer J, Tchale H. 2009. The economics of soil fertility management in Malawi. Appl Econ Perspect
Policy. 31(3):535–560. doi: 10.1111/j.1467-9353.2009.01452.x.
Scheiterle L, H€aring V, Birner R, Bosch C. 2019. Soil, striga, or subsidies? Determinants of maize product-
ivity in Northern Ghana. Agric Econ. 50(4):479–494. doi: 10.1111/agec.12504.
Scheiterle L, Birner R. 2018. Assessment of Ghana’s comparative ddvantage in maize production and the
role of fertilizers. Sustainability. 10(11):4181. doi: 10.3390/su10114181.
Setsoafia ED, Ma W, Renwick A. 2022. Effects of sustainable agricultural practices on farm income and
food security in Northern Ghana. Agric Econ. 10(1):1–15. doi: 10.1186/S40100-022-00216-9/TABLES/4.
Shi W, Tao F. 2014. Vulnerability of African maize yield to climate change and variability during 1961-
2010. Food Sec. 6(4):471–481. doi: 10.1007/S12571-014-0370-4/METRICS.
Silberg TR, Richardson RB, Hockett M, Snapp SS. 2017. Sustainability maize-legume intercropping in cen-
tral Malawi: determinants of practice. Int J Agric. 15(6):662–680. doi: 10.1080/14735903.2017.1375070.
Snapp S, et al. 2014. Maize yield response to nitrogen in Malawi’s smallholder production systems, MaSSP.
9. Washington, DC. Available at: http://ebrary.ifpri.org/cdm/ref/collection/p15738coll2/id/128436.
(Accessed: 20 February 2023).
18 S. GACHOKI AND F. MUTHONI
Srivastava AK, Mboh CM, Gaiser T, Ewert F. 2017. Impact of climatic variables on the spatial and tem-
poral variability of crop yield and biomass gap in Sub-Saharan Africa- a case study in Central Ghana.
Field Crops Research. 203:33–46. doi: 10.1016/j.fcr.2016.11.010.
Tamene L, Mponela P, Ndengu G, Kihara J. 2016. Assessment of maize yield gap and major determinant
factors between smallholder farmers in the Dedza district of Malawi. Nutr Cycl Agroecosyst. 105(3):
291–308. doi: 10.1007/s10705-015-9692-7.
Tinonin C, et al. 2016. Africa RISING Baseline Evaluation Survey (ARBES) report for Ghana. International
Food Policy Research Institute. Available at: https://cgspace.cgiar.org/handle/10568/75528. (Accessed: 8
March 2023).
Tittonell P, Giller KE. 2013. When yield gaps are poverty traps: the paradigm of ecological intensification
in African smallholder agriculture. Field Crops Res. 143:76–90. doi: 10.1016/j.fcr.2012.10.007.
Vergopolan N, Xiong S, Estes L, Wanders N, Chaney NW, Wood EF, Konar M, Caylor K, Beck HE, Gatti
N, et al. 2021. Field-scale soil moisture bridges the spatial-scale gap between drought monitoring and
agricultural yields. Hydrol Earth Syst Sci. 25(4):1827–1847. doi: 10.5194/hess-25-1827-2021.
Vuntade D, Mzuza MK, Vuntade D, Mzuza MK. 2022. Factors affecting adoption of Conservation
Agriculture practices in Mpatsa extension planning area, Nsanje, Southern Malawi. GEP. 10(03):96–
110. doi: 10.4236/gep.2022.103008.
Wang H, Snapp SS, Fisher M, Viens F. 2019. A Bayesian analysis of longitudinal farm surveys in Central
Malawi reveals yield determinants and site-specific management strategies. PLoS One. 14(8):e0219296.
doi: 10.1371/journal.pone.0219296.
Warnatzsch EA, Reay DS, Camardo Leggieri M, Battilani P. 2020. Climate change impact on aflatoxin
contamination risk in Malawi’s maize crops. Front Sustain Food Syst. 4:238. doi: 10.3389/FSUFS.2020.
591792/BIBTEX.
Warnatzsch EA, Reay DS. 2020. Assessing climate change projections and impacts on Central Malawi’s
maize yield: the risk of maladaptation. Sci Total Environ. 711:134845. doi: 10.1016/j.scitotenv.2019.
134845.
De Weerdt J, Duchoslav J. 2022. Are fertilizer subsidies in Malawi value for money? doi: 10.2499/
P15738COLL2.135960.
White S. 2019. A TEEBAgriFood analysis of the Malawi maize agri-food system. Available at: https://futur-
eoffood.org/wp-content/uploads/2021/01/GA_TEEB_MalawiMaize201903.pdf. (Accessed: 20 February
2023).
Yeboah S, Ennin SA, Ibrahim A, Oteng-Darko P, Mutyambai D, Khan ZR, Mochiah MB, Ekesi S, Niassy
S. 2021. Effect of spatial arrangement of push-pull companion plants on fall armyworm control and
agronomic performance of two maize varieties in Ghana. Crop Prot. 145:105612. doi: 10.1016/j.cropro.
2021.105612.
Zhang L, Zhang Z, Luo Y, Cao J, Tao F. 2019. Combining optical, fluorescence, thermal satellite, and
environmental data to predict county-level maize yield in China using machine learning approaches.
Remote Sens. 12(1):21. doi: 10.3390/rs12010021.
GEOCARTO INTERNATIONAL 19
Appendix 1. Histograms showing the distribution of the continuous
household and satellite-based across the different households in Ghana and
Malawi
20 S. GACHOKI AND F. MUTHONI
Appendix 2. Scatter plots for the predicted versus observed maize yield for
Northern Ghana and Malawi in 2013 and 2019 when using all predictor
variables