Search

Remote sensing offers a low-cost method for estimating yields at large spatio-temporal scales. Here, we examined the ability of Sentinel-2 satellite imagery to map field-level maize yields across smallholder farms in two regions in Oromia district, Ethiopia. We evaluated how effectively different indices, the MTCI, GCVI, and NDVI, and different models, linear regression and random forest regression, can be used to map field-level yields. We also examined if models improved by adding weather and soil data and how generalizable our models were if trained in one region and applied to another region, where no data were used for model calibration. We found that random forest regression models that used monthly MTCI composites led to the highest yield prediction accuracies (R2 up to 0.63), particularly when using only localized data for training the model. These models were not very generalizable, especially when applied to regions that had significant haze remaining in the imagery. We also found that adding soil and weather data did little to improve model fit. Our results highlight the ability of Sentinel-2 imagery to map field-level yields in smallholder systems, though accuracies are limited in regions with high cloud cover and haze. [ABSTRACT FROM AUTHOR]

The livestock-dairy sector in Sub-Saharan Africa, particularly in Rwanda, is experiencing rapid growth due to population expansion, urbanisation, and changing food preferences. The unmet local production demands are causing soil and water pollution, competition for biomass, land, and water, but also grassland degradation, biodiversity loss, and increased GHGs emissions. Rwanda has the lowest productivity in the region, largely due to inadequate and poor-quality livestock feed resources. To increase animal productivity, promoting forage species with higher nutritional value and better adaptation to drought-prone and poor-fertility soils could be beneficial. Using a mixed-methods approach, the study explores Brachiaria forage adoption and profitability and analyses policy objectives and measures to overcome adoption barriers and promote the transition from subsistence to market-oriented systems. Results show that Brachiaria, although advantageous from an economic point of view, is characterised by very low adoption rates. Furthermore, access to extension programmes is limited and often not supported by adequate incentives. To overcome such barriers, policy interventions should be harmonised and information and knowledge management prioritised, public and private extension and advisory services (EASs) programmes coordinated, agricultural input subsidies increased, and institutional coordination promoted to enhance climate-smart animal feeding. [ABSTRACT FROM AUTHOR]

Soils on many smallholder farms in Southern Africa are severely depleted in plant nutrients, in particular phosphorus (P), following years of maize monocropping with little or no fertilizer input. Past studies suggest that pigeon pea (Cajanus cajan (L.) Millsp.) may increase plant-available P. Pigeon pea is not a common crop in much of Southern Africa, and the effect of locally grown pigeon pea varieties on plant-available P is unknown. We assessed the changes in plant-available P after growing pigeon pea varieties MPPV-2, MPPV-3, and Babati White in Zambia, viz. Lixisols of Choma and Mkushi, Acrisols of Chipata and Kasama, and Arenosols of Kaoma. The selected soils were not fertilized. Baseline soils (0–20 cm), sampled after long-term maize monocropping and soils from the same fields after growing pigeon pea were collected from field trials in Kaoma, Chipata, Choma, and Mkushi and analyzed for plant-available P. Further, a greenhouse study was conducted with soils from Kasama, Choma, Kaoma, and Chipata, under which soil P was determined before and after growing pigeon pea, soybean (Dina), and maize (SC 419) without fertilizer addition. Pigeon pea under field studies had no significant (p > 0.05) effect on plant-available P in Choma, Kaoma, and Chipata. In Mkushi, pigeon pea cropping resulted in a 47.5% significant decline (p ≤ 0.05) in plant-available P, amounting to a loss of 11.2 kg ha−1. The greenhouse study showed a significant decline (p ≤ 0.001) in plant-available P after seven weeks of maize growth, while there was no significant (p > 0.05) effect on plant-available P after soybean and pigeon pea cropping. The latter was primarily due to the significantly higher P uptake associated with larger biomass production of maize after seven weeks in the greenhouse. During the initial seven weeks, pigeon pea biomass had significantly higher P concentrations than maize. Thus, P deficiency symptoms were exhibited in maize, while pigeon pea appeared healthy. However, mobilized P, calculated as the sum of plant P and soil P after cropping minus soil P before planting, was significantly lower (p ≤ 0.01) in pigeon pea compared to soybean and maize. Synthesizing field and greenhouse experiments suggests that there is a low net decline of plant-available P from soils after pigeon pea cropping. Therefore, rotation with these pigeon pea varieties could be beneficial to resource-poor farmers due to low P removal and its ability to grow in P-deficient soil. [ABSTRACT FROM AUTHOR]

China is currently experiencing a severe issue of excessive fertilization. Variable rate fertilization (VRF) technology is key to solving this issue in precision agriculture, and one way to implement VRF is through management zone (MZ) delineation. This study is aimed at evaluating the feasibility and potential benefits of VRF based on site-specific MZs in smallholder farm fields. This study determined the amounts of basal and top-dressing fertilizers in different spatial units, based on soil nutrient MZs and crop growth MZs, respectively. The potential agronomic, economic, and environmental advantages of spatial variable rate fertilization were further assessed by comparing the farmer's treatment, the expert's treatment, and the variable rate fertilization treatment based on management zones (VR-MZ). The results showed that VR-MZ reduced the use of nitrogen (N), phosphorus (P), and potassium (K) fertilizers by 22.90–43.95%, 59.11–100%, and 8.21–100%, respectively, and it also increased the use efficiency of N, P, and K by 12.27–28.71, 89.64–176.85, and 5.48–266.89 kg/kg, respectively, without yield loss. The net incomes of VR-MZ were 15.5–449.61 USD ha−1 higher than that of traditional spatially uniform rate fertilization. Meanwhile, less nitrous oxide emission (23.50–45.81%), ammonia volatilization (19.38–51.60%), and nitrate ion leaching amounts (28.77–53.98%) were found in VR-MZ compared to those in uniform fertilization. The results suggest that the VR-MZ has great potential for saving fertilizers, significantly increasing farmers' net income, reducing environmental pollution, and promoting the sustainable use of resources. This study provides a theoretical basis and technical support for exploring a VRF suitable for village-scale farming. [ABSTRACT FROM AUTHOR]

Banana (and plantain, Musa spp.), in sub-Saharan Africa (SSA), is predominantly grown as a mixed crop by smallholder farmers in backyards and small farmlands, typically ranging from 0.2 ha to 3 ha. The crop is affected by several pests and diseases, including the invasive banana bunchy top virus (BBTV, genus Babuvirus), which is emerging as a major threat to banana production in SSA. The BBTV outbreak in West Africa was first recorded in the Benin Republic in 2010 and has spread to the adjoining territories of Nigeria and Togo. Regular surveillance, conducted as part of the containment efforts, requires the identification of banana fields for disease assessment. However, small and fragmented production spread across large areas poses complications for identifying all banana farms using conventional field survey methods, which is also time-consuming and expensive. In this study, we developed a remote sensing approach and machine learning (ML) models that can be used to identify banana fields for targeted BBTV surveillance. We used medium-resolution synthetic aperture radar (SAR), Sentinel 2A satellite imagery, and high-resolution RGB and multispectral aerial imagery from an unmanned aerial vehicle (UAV) to develop an operational banana mapping framework by combining the UAV, SAR, and Sentinel 2A data with the Support Vector Machine (SVM) and Random Forest (RF) machine learning algorithms. The ML algorithms performed comparatively well in classifying the land cover, with a mean overall accuracy (OA) of about 93% and a Kappa coefficient (KC) of 0.89 for the UAV data. The model using fused SAR and Sentinel 2A data gave an OA of 90% and KC of 0.86. The user accuracy (UA) and producer accuracy (PA) for the banana class were 83% and 78%, respectively. The BBTV surveillance teams used the banana mapping framework to identify banana fields in the BBTV-affected southwest Ogun state of Nigeria, which helped in detecting 17 sites with BBTV infection. These findings suggest that the prediction of banana and other crops in the heterogeneous smallholder farming systems is feasible, with the precision necessary to guide BBTV surveillance in large areas in SSA. [ABSTRACT FROM AUTHOR]

The mapping of field boundaries can provide important information for increasing food production and security in agricultural systems across the globe. Remote sensing can provide a viable way to map field boundaries across large geographic extents, yet few studies have used satellite imagery to map boundaries in systems where field sizes are small, heterogeneous, and irregularly shaped. Here we used very-high-resolution WorldView-3 satellite imagery (0.5 m) and a mask region-based convolutional neural network (Mask R-CNN) to delineate smallholder field boundaries in Northeast India. We found that our models had overall moderate accuracy, with average precision values greater than 0.67 and F1 Scores greater than 0.72. We also found that our model performed equally well when applied to another site in India for which no data were used in the calibration step, suggesting that Mask R-CNN may be a generalizable way to map field boundaries at scale. Our results highlight the ability of Mask R-CNN and very-high-resolution imagery to accurately map field boundaries in smallholder systems. [ABSTRACT FROM AUTHOR]

Accurate measurements of crop production in smallholder farming systems are critical to the understanding of yield constraints and, thus, setting the appropriate agronomic investments and policies for improving food security and reducing poverty. Nevertheless, mapping the yields of smallholder farms is challenging because of factors such as small field sizes and heterogeneous landscapes. Recent advances in fine-resolution satellite sensors offer promise for monitoring and characterizing the production of smallholder farms. In this study, we investigated the utility of different sensors, including the commercial Skysat and RapidEye satellites and the publicly accessible Sentinel-2, for tracking smallholder maize yield variation throughout a ~40,000 km² western Kenya region. We tested the potential of two types of multiple regression models for predicting yield: (i) a "calibrated model", which required ground-measured yield and weather data for calibration, and (ii) an "uncalibrated model", which used a process-based crop model to generate daily vegetation index and end-of-season biomass and/or yield as pseudo training samples. Model performance was evaluated at the field, division, and district scales using a combination of farmer surveys and crop cuts across thousands of smallholder plots in western Kenya. Results show that the "calibrated" approach captured a significant fraction (R² between 0.3 and 0.6) of yield variations at aggregated administrative units (e.g., districts and divisions), while the "uncalibrated" approach performed only slightly worse. For both approaches, we found that predictions using the MERIS Terrestrial Chlorophyll Index (MTCI), which included the red edge band available in RapidEye and Sentinel-2, were superior to those made using other commonly used vegetation indices. We also found that multiple refinements to the crop simulation procedures led to improvements in the "uncalibrated" approach. We identified the prevalence of small field sizes, intercropping management, and cloudy satellite images as major challenges to improve the model performance. Overall, this study suggested that high-resolution satellite imagery can be used to map yields of smallholder farming systems, and the methodology presented in this study could serve as a good foundation for other smallholder farming systems in the world. [ABSTRACT FROM AUTHOR]

Remote sensing offers a low-cost method for developing spatially continuous crop production statistics across large areas and through time. Nevertheless, it has been difficult to characterize the production of individual smallholder farms, given that the land-holding size in most areas of South Asia (<2 ha) is smaller than the spatial resolution of most freely available satellite imagery, like Landsat and MODIS. In addition, existing methods to map yield require field-level data to develop and parameterize predictive algorithms that translate satellite vegetation indices to yield, yet these data are costly or difficult to obtain in many smallholder systems. To overcome these challenges, this study explores two issues. First, we employ new high spatial (2 m) and temporal (bi-weekly) resolution micro-satellite SkySat data to map sowing dates and yields of smallholder wheat fields in Bihar, India in the 2014–2015 and 2015–2016 growing seasons. Second, we compare how well we predict sowing date and yield when using ground data, like crop cuts and self-reports, versus using crop models, which require no on-the-ground data, to develop and parameterize prediction models. Overall, sow dates were predicted well (R2 = 0.41 in 2014–2015 and R2 = 0.62 in 2015–2016), particularly when using models that were parameterized using self-report sow dates collected close to the time of planting and when using imagery that spanned the entire growing season. We were also able to map yields fairly well (R2 = 0.27 in 2014–2015 and R2 = 0.33 in 2015–2016), with crop cut parameterized models resulting in the highest accuracies. While less accurate, we were able to capture the large range in sow dates and yields across farms when using models parameterized with crop model data and these estimates were able to detect known relationships between management factors (e.g., sow date, fertilizer, and irrigation) and yield. While these results are specific to our study site in India, it is likely that the methods employed and the lessons learned are applicable to smallholder systems more generally across the globe. This is of particular interest given that similar high spatio-temporal resolution micro-satellite data will become increasingly available in the coming years. [ABSTRACT FROM AUTHOR]

Explicit spatial information about crop types on smallholder farms is important for the development of local precision agriculture. However, due to highly fragmented and heterogeneous cropland landscapes, fine-scale mapping of smallholder crops, based on low- and medium-resolution satellite images and relying on a single machine learning (ML) classifier, generally fails to achieve satisfactory performance. This paper develops an ensemble ML-based framework to improve the accuracy of parcel-level smallholder crop mapping from very high spatial resolution (VHSR) images. A typical smallholder agricultural area in central China covered by WorldView-2 images is selected to demonstrate our approach. This approach involves the task of distinguishing eight crop-level agricultural land use types. To this end, six widely used individual ML classifiers are evaluated. We further improved their performance by independently implementing bagging and stacking ensemble learning (EL) techniques. The results show that the bagging models improved the performance of unstable classifiers, but these improvements are limited. In contrast, the stacking models perform better, and the Stacking #2 model (overall accuracy = 83.91%, kappa = 0.812), which integrates the three best-performing individual classifiers, performs the best of all of the built models and improves the classwise accuracy of almost all of the land use types. Since classification performance can be significantly improved without adding costly data collection, stacking-ensemble mapping approaches are valuable for the spatial management of complex agricultural areas. We also demonstrate that using geometric and textural features extracted from VHSR images can improve the accuracy of parcel-level smallholder crop mapping. The proposed framework shows the great potential of combining EL technology with VHSR imagery for accurate mapping of smallholder crops, which could facilitate the development of parcel-level crop identification systems in countries dominated by smallholder agriculture. [ABSTRACT FROM AUTHOR]

Remote sensing offers a way to map crop types across large spatio-temporal scales at low costs. However, mapping crop types is challenging in heterogeneous, smallholder farming systems, such as those in India, where field sizes are often smaller than the resolution of historically available imagery. In this study, we examined the potential of relatively new, high-resolution imagery (Sentinel-1, Sentinel-2, and PlanetScope) to identify four major crop types (maize, mustard, tobacco, and wheat) in eastern India using support vector machine (SVM). We found that a trained SVM model that included all three sensors led to the highest classification accuracy (85%), and the inclusion of Planet data was particularly helpful for classifying crop types for the smallest farms (<600 m2). This was likely because its higher spatial resolution (3 m) could better account for field-level variations in smallholder systems. We also examined the impact of image timing on the classification accuracy, and we found that early-season images did little to improve our models. Overall, we found that readily available Sentinel-1, Sentinel-2, and Planet imagery were able to map crop types at the field-scale with high accuracy in Indian smallholder systems. The findings from this study have important implications for the identification of the most effective ways to map crop types in smallholder systems. [ABSTRACT FROM AUTHOR]

Assessing and prescribing fertilizer use is critical to profitable and sustainable coffee production, and this is becoming a priority concern for the Robusta coffee industry. In this study, annual survey data of 798 farms across selected Robusta coffee-producing provinces in Vietnam and Indonesia between 2008 and 2017 were used to comparatively assess the fertilizer management strategies in these countries. Specifically, we aimed to characterize fertilizer use patterns in the key coffee-growing provinces and discuss the potential for improving nutrient management practices. Four types of chemical (NPK, super phosphate, potassium chloride and urea) and two of natural (compost and lime) fertilizers were routinely used in Vietnam. In Indonesia, NPK and urea were supplemented only with compost. Farmers in Vietnam applied unbalanced quantities of chemical fertilizers (i.e., higher rates than recommended) and at a constant rate between years whereas Indonesian farmers applied well below the recommended rates because of poor accessibility and financial support. The overuse of chemical fertilizers in Vietnam threatens the sustainability of Robusta coffee farming. Nevertheless, there is a potential for improvement in both countries in terms of nutrient management and sustainability of Robusta coffee production by adopting the best local fertilizer management practices. [ABSTRACT FROM AUTHOR]