Mapping land suitability for informal, small-scale irrigation development using spatial modelling and machine learning in the Upper East Region, Ghana.

Small-scale irrigation has gained momentum in recent years as one of the development priorities in Sub-Saharan Africa. However, farmer-led irrigation is often informal with little support from extension services and a paucity of data on land suitability for irrigation. To map the spatial explicit suitability for dry season small-scale irrigation, we developed a method using an ensemble of boosted regression trees, random forest, and maximum entropy machine learning models for the Upper East Region of Ghana. Both biophysical predictors including surface and groundwater availability, climate, topography and soil properties, and socio-economic predictors which represent demography and infrastructure development such as accessibility to cities and proximity to roads were considered. We assessed that 179,584 ± 49,853 ha is suitable for dry-season small-scale irrigation development when only biophysical variables are considered, and 158,470 ± 27,222 ha when socio-economic variables are included alongside the biophysical predictors, representing 77-89% of the current rainfed-croplands. Travel time to cities, accessibility to small reservoirs, exchangeable sodium percentage, surface runoff that can be potentially stored in reservoirs, population density, proximity to roads, and elevation percentile were the top predictors of small-scale irrigation suitability. These results suggested that the availability of water alone is not a sufficient indicator for area suitability for small-scale irrigation. This calls for strategic road infrastructure development and an improvement in the support to farmers for market accessibility. The suitability for small-scale irrigation should be put in the local context of market availability, demographic indicators, and infrastructure development.

Mapping suitability for rice production in inland valley landscapes in Benin and Togo using environmental niche modeling.

Inland valleys (IVs) in Africa are important landscapes for rice cultivation and are targeted by national governments to attain self-sufficiency. Yet, there is limited information on the spatial distribution of IVs suitability at the national scale. In the present study, we developed an ensemble model approach to characterize the IVs suitability for rainfed lowland rice using 4 machine learning algorithms based on environmental niche modeling (ENM) with presence-only data and background sample, namely Boosted Regression Tree (BRT), Generalized Linear Model (GLM), Maximum Entropy (MAXNT) and Random Forest (RF). We used a set of predictors that were grouped under climatic variables, agricultural water productivity and soil water content, soil chemical properties, soil physical properties, vegetation cover, and socio-economic variables. The Area Under the Curves (AUC) evaluation metrics for both training and testing were respectively 0.999 and 0.873 for BRT, 0.866 and 0.816 for GLM, 0.948 and 0.861 for MAXENT and 0.911 and 0.878 for RF. Results showed that proximity of inland valleys to roads and urban centers, elevation, soil water holding capacity, bulk density, vegetation index, gross biomass water productivity, precipitation of the wettest quarter, isothermality, annual precipitation, and total phosphorus among others were major predictors of IVs suitability for rainfed lowland rice. Suitable IVs areas were estimated at 155,000-225,000 Ha in Togo and 351,000-406,000 Ha in Benin. We estimated that 53.8% of the suitable IVs area is needed in Togo to attain self-sufficiency in rice while 60.1% of the suitable IVs area is needed in Benin to attain self-sufficiency in rice. These results demonstrated the effectiveness of an ensemble environmental niche modeling approach that combines the strengths of several models.

A geospatial dataset of inland valleys in four zones in Benin, Sierra Leone and Mali.

The dataset described in this data article represents four agricultural zones in West-Africa that are located in three countries: Benin, Mali and Sierra Leone. The dataset was created through a research collaboration between the Africa Rice Center (AfricaRice), Sierra Leone Agricultural Research Institute (SLARI) and the Institute for Rural Economy (IER). The dataset was compiled to investigate the potential for rice production in inland valleys of the three countries. The results of the investigation were published in Dossou-Yovo et al. (2017) and Djagba et al. (2018). The dataset describes the biophysical and socioeconomic conditions of 499 inland valleys in the four agricultural zones. In each inland valley data were collected through a focus group interview with a minimum of three farmers. In 499 interviews a total of 7496 farmers participated. The location of each inland valley was determined with handheld GPS devices. The geographic locations were used to extract additional parameters from digital maps on soils, elevation, population density, rainfall, flow accumulation, and distances to roads, market places, rice mills, chemical input stores, and settlements. The dataset contains 65 parameters in four themes (location, biophysical characteristics, socioeconomic characteristics, and inland valley land development and use). The GPS coordinates indicate the location of an inland valley, but they do not lead to the location of individual fields of farmers that were interviewed. The dataset is publicly shared as Supplementary data to this data article.

A geospatial database of drought occurrence in inland valleys in Mali, Burkina Faso and Nigeria.

The data described in this article are related to drought occurrence in inland valleys and farmers adaptation strategies. The data were collected in 300 inland valleys distributed in 14 regions of West Africa. The data were collected in two phases. In the first phase, 300 inland valleys were identified in 14 regions and their locations were determined with handheld GPS devices. Questionnaires and informal interviews were administered to inland valleys users to collect data on physical and socio-economic characteristics, hydrology, farmers experience with drought affecting rice production in inland valleys and adaptation strategies. In the second phase, the locations of the inland valleys were imported in a GIS environment and were used to extract additional parameters on soil characteristics and water demand from the Shuttle Radar Topography Mission (SRTM), Africa Soil Information Service (africasoils.net) and POWER database (http://power.larc.nasa.gov). In total, the dataset contains 41 variables divided into seven themes: farmers' experience with drought, adaptive management of rice farmers to drought, physical characteristics, hydrology, management practices, socio-economic characteristics and weather data of inland valleys.

Impacts of climate change on cropping patterns in a tropical, sub-humid watershed.

In recent decades, there have been substantial increases in crop production in sub-Saharan Africa (SSA) as a result of higher yields, increased cropping intensity, expansion of irrigated cropping systems, and rainfed cropland expansion. Yet, to date much of the research focus of the impact of climate change on crop production in the coming decades has been on crop yield responses. In this study, we analyse the impact of climate change on the potential for increasing rainfed cropping intensity through sequential cropping and irrigation expansion in central Benin. Our approach combines hydrological modelling and scenario analysis involving two Representative Concentration Pathways (RCPs), two water-use scenarios for the watershed based on the Shared Socioeconomic Pathways (SSPs), and environmental water requirements leading to sustained streamflow. Our analyses show that in Benin, warmer temperatures will severely limit crop production increases achieved through the expansion of sequential cropping. Depending on the climate change scenario, between 50% and 95% of cultivated areas that can currently support sequential cropping or will need to revert to single cropping. The results also show that the irrigation potential of the watershed will be at least halved by mid-century in all scenario combinations. Given the urgent need to increase crop production to meet the demands of a growing population in SSA, our study outlines challenges and the need for planned development that need to be overcome to improve food security in the coming decades.

Impacts of climate change on rice production in Africa and causes of simulated yield changes.

This study is the first of its kind to quantify possible effects of climate change on rice production in Africa. We simulated impacts on rice in irrigated systems (dry season and wet season) and rainfed systems (upland and lowland). We simulated the use of rice varieties with a higher temperature sum as adaptation option. We simulated rice yields for 4 RCP climate change scenarios and identified causes of yield declines. Without adaptation, shortening of the growing period due to higher temperatures had a negative impact on yields (-24% in RCP 8.5 in 2070 compared with the baseline year 2000). With varieties that have a high temperature sum, the length of the growing period would remain the same as under the baseline conditions. With this adaptation option rainfed rice yields would increase slightly (+8%) but they remain subject to water availability constraints. Irrigated rice yields in East Africa would increase (+25%) due to more favourable temperatures and due to CO2 fertilization. Wet season irrigated rice yields in West Africa were projected to change by -21% or +7% (without/with adaptation). Without adaptation irrigated rice yields in West Africa in the dry season would decrease by -45% with adaptation they would decrease significantly less (-15%). The main cause of this decline was reduced photosynthesis at extremely high temperatures. Simulated heat sterility hardly increased and was not found a major cause for yield decline. The implications for these findings are as follows. For East Africa to benefit from climate change, improved water and nutrient management will be needed to benefit fully from the more favourable temperatures and increased CO2 concentrations. For West Africa, more research is needed on photosynthesis processes at extreme temperatures and on adaptation options such as shifting sowing dates.

Quantifying trade-offs between future yield levels, food availability and forest and woodland conservation in Benin.

Meeting the dual objectives of food security and ecosystem protection is a major challenge in sub-Saharan Africa (SSA). To this end agricultural intensification is considered desirable, yet, there remain uncertainties regarding the impact of climate change on opportunities for agricultural intensification and the adequacy of intensification options given the rapid population growth. We quantify trade-offs between levels of yield gap closure, food availability and forest and woodland conservation under different scenarios. Each scenario is made up of a combination of variants of four parameters i.e. (1) climate change based on Representative Concentration Pathways (RCPs); (2) population growth based on Shared Socioeconomic Pathways (SSPs); (3) cropland expansion with varying degrees of deforestation; and (4) different degrees of yield gap closure. We carry out these analyses for three major food crops, i.e. maize, cassava and yam, in Benin. Our analyses show that in most of the scenarios, the required levels of yield gap closures required to maintain the current levels of food availability can be achieved by 2050 by maintaining the average rate of yield increases recorded over the past two and half decades in addition to the current cropping intensity. However, yields will have to increase at a faster rate than has been recorded over the past two and half decades in order to achieve the required levels of yield gap closures by 2100. Our analyses also show that without the stated levels of yield gap closure, the areas under maize, cassava and yam cultivation will have to increase by 95%, 102% and 250% respectively in order to maintain the current levels of per capita food availability. Our study shows that food security outcomes and forest and woodland conservation goals in Benin and likely the larger SSA region are inextricably linked together and require holistic management strategies that considers trade-offs and co-benefits.

RiceAtlas, a spatial database of global rice calendars and production.

Knowing where, when, and how much rice is planted and harvested is crucial information for understanding the effects of policy, trade, and global and technological change on food security. We developed RiceAtlas, a spatial database on the seasonal distribution of the world's rice production. It consists of data on rice planting and harvesting dates by growing season and estimates of monthly production for all rice-producing countries. Sources used for planting and harvesting dates include global and regional databases, national publications, online reports, and expert knowledge. Monthly production data were estimated based on annual or seasonal production statistics, and planting and harvesting dates. RiceAtlas has 2,725 spatial units. Compared with available global crop calendars, RiceAtlas is nearly ten times more spatially detailed and has nearly seven times more spatial units, with at least two seasons of calendar data, making RiceAtlas the most comprehensive and detailed spatial database on rice calendar and production.