Bee keeping is indispensable to global food production. It is an alternate income source, especially in rural underdeveloped African settlements, and an important forest conservation incentive. However, dwindling honeybee colonies around the world are attributed to pests and diseases whose spatial distribution and influences are not well established. In this study, we used remotely sensed data to improve the reliability of pest ecological niche (EN) models to attain reliable pest distribution maps. Occurrence data on four pests (Aethina tumida, Galleria mellonella, Oplostomus haroldi and Varroa destructor) were collected from apiaries within four main agro-ecological regions responsible for over 80% of Kenya’s bee keeping. Africlim bioclimatic and derived normalized difference vegetation index (NDVI) variables were used to model their ecological niches using Maximum Entropy (MaxEnt). Combined precipitation variables had a high positive logit influence on all remotely sensed and biotic models’ performance. Remotely sensed vegetation variables had a substantial effect on the model, contributing up to 40.8% for G. mellonella and regions with high rainfall seasonality were predicted to be high-risk areas. Projections (to 2055) indicated that, with the current climate change trend, these regions will experience increased honeybee pest risk. We conclude that honeybee pests could be modelled using bioclimatic data and remotely sensed variables in MaxEnt. Although the bioclimatic data were most relevant in all model results, incorporating vegetation seasonality variables to improve mapping the ‘actual’ habitat of key honeybee pests and to identify risk and containment zones needs to be further investigated.

Cropping systems information on explicit scales is an important but rarely available variable in many crops modeling routines and of utmost importance for understanding pests and disease propagation mechanisms in agro-ecological landscapes. In this study, high spatial and temporal resolution RapidEye bio-temporal data were utilized within a novel 2-step hierarchical random forest (RF) classification approach to map areas of mono- and mixed maize cropping systems. A small-scale maize farming site in Machakos County, Kenya was used as a study site. Within the study site, field data was collected during the satellite acquisition period on general land use/land cover (LULC) and the two cropping systems. Firstly, non-cropland areas were masked out from other land use/land cover using the LULC mapping result. Subsequently an optimized RF model was applied to the cropland layer to map the two cropping systems (2nd classification step). An overall accuracy of 93% was attained for the LULC classification, while the class accuracies (PA: producer’s accuracy and UA: user’s accuracy) for the two cropping systems were consistently above 85%. We concluded that explicit mapping of different cropping systems is feasible in complex and highly fragmented agro-ecological landscapes if high resolution and multi-temporal satellite data such as 5 m RapidEye data is employed. Further research is needed on the feasibility of using freely available 10–20 m Sentinel-2 data for wide-area assessment of cropping systems as an important variable in numerous crop productivity models.

Rift Valley fever (RVF) is a mosquito-borne infection with great impact on animal and human health. The objectives of this study were to identify ecological factors that explain the risk of RVF outbreaks in eastern and central Kenya and to produce a spatially explicit risk map. The sensitivity of seven selected ecological variables to RVF occurrence was assessed by generalized linear modelling (GLM). Vegetation seasonality variables (from normalized difference vegetation index (NDVI) data) and 'evapotranspiration' (ET) (metrics) were obtained from 0.25-1km MODIS satellite data observations; 'livestock density' (N/km(2)), 'elevation' (m), and 'soil ratio' (fraction of all significant soil types within a certain county as a function of the total area of that county) were used as covariates. 'Livestock density', 'small vegetation integral', and the second principal component of ET were the most significant determinants of RVF occurrence in Kenya (all p ≤ 0.01), with high RVF risk areas identified in the counties of Tana River, Garissa, Isiolo, and Lamu. Wet soil fluxes measured with ET and vegetation seasonality variables could be used to map RVF risk zones on a sub-regional scale. Future outbreaks could be better managed if relevant RVF variables are integrated into early warning systems.

Currently there is a lack of quantitative information regarding the driving factors of vegetation dynamics in post-Soviet Central Asia. Insufficient knowledge also exists concerning vegetation variability across sub-humid to arid climatic gradients as well as vegetation response to different land uses, from natural rangelands to intensively irrigated croplands. In this study, we analyzed the environmental drivers of vegetation dynamics in five Central Asian countries by coupling key vegetation parameter “overall greenness” derived from Moderate Resolution Imaging Spectroradiometer (MODIS) Normalized Difference Vegetation Index (NDVI time series data, with its possible factors across various management and climatic gradients. We developed nine generalized least-squares random effect (GLS-RE) models to analyze the relative impact of environmental factors on vegetation dynamics. The obtained results quantitatively indicated the extensive control of climatic factors on managed and unmanaged vegetation cover across Central Asia. The most diverse vegetation dynamics response to climatic variables was observed for “intensively managed irrigated croplands”. Almost no differences in response to these variables were detected for managed non-irrigated vegetation and unmanaged (natural) vegetation across all countries. Natural vegetation and rainfed non-irrigated crop dynamics were principally associated with temperature and precipitation parameters. Variables related to temperature had the greatest relative effect on irrigated croplands and on vegetation cover within the mountainous zone. Further research should focus on incorporating the socio-economic factors discussed here in a similar analysis.

The quantity of land covered by various crops in a specific time span, referred to as a cropping pattern, dictates the level of agricultural production. However, retrieval of this information at a landscape scale can be challenging, especially when high spatial resolution imagery is not available. This study hypothesized that utilizing the unique advantages of multi-date and medium spatial resolution freely available Sentinel-2 (S2) reflectance bands (S2 bands), their vegetation indices (VIs) and vegetation phenology (VP) derivatives, and Sentinel-1 (S1) backscatter data would improve cropping pattern mapping in heterogeneous landscapes using robust machine learning algorithms, i.e., the guided regularized random forest (GRRF) for variable selection and the random forest (RF) for classification. This study’s objective was to map cropping patterns within three sub-counties in Murang’a County, a typical African smallholder heterogeneous farming area, in Kenya. Specifically, the performance of eight classification scenarios for mapping cropping patterns was compared, namely: (i) only S2 bands; (ii) S2 bands and VIs; (iii) S2 bands and VP; (iv) S2 bands and S1; (v) S2 bands, VIs, and S1; (vi) S2 bands, VP, and S1; (vii) S2 bands, VIs, and VP; and (viii) S2 bands, VIs, VP, and S1. Reference data of the dominant cropping patterns and non-croplands were collected. The GRRF algorithm was used to select the optimum variables in each scenario, and the RF was used to perform the classification for each scenario. The highest overall accuracy was 94.33% with Kappa of 0.93, attained using the GRRF-selected variables of scenario (v) S2, VIs, and S1. Furthermore, McNemar’s test of significance did not show significant differences (p ≤ 0.05) among the tested scenarios. This study demonstrated the strength of GRRF in selecting the most important variables and the synergetic advantage of S2 and S1 derivatives to accurately map cropping patterns in small-scale farming-dominated landscapes. Consequently, the cropping pattern mapping approach can be used in other sites of relatively similar agro-ecological conditions. Additionally, these results can be used to understand the sustainability of food systems and to model the abundance and spread of crop insect pests, diseases, and pollinators.