Tag: crop yields
Soil nutrient maps of Sub-Saharan Africa: assessment of soil nutrient content at 250 m spatial resolution using machine learning
Spatial predictions of soil macro and micro-nutrient content across Sub-Saharan Africa at 250 m spatial resolution and for 0–30 cm depth interval are presented. Predictions were produced for 15 target nutrients: organic carbon (C) and total (organic) nitrogen (N), total phosphorus (P), and extractable—phosphorus (P), potassium (K), calcium (Ca), magnesium (Mg), sulfur (S), sodium (Na), iron (Fe), manganese (Mn), zinc (Zn), copper (Cu), aluminum (Al) and boron (B). Model training was performed using soil samples from ca. 59,000 locations (a compilation of soil samples from the AfSIS, EthioSIS, One Acre Fund, VitalSigns and legacy soil data) and an extensive stack of remote sensing covariates in addition to landform, lithologic and land cover maps. An ensemble model was then created for each nutrient from two machine learning algorithms—random forest and gradient boosting, as implemented in R packages ranger and xgboost—and then used to generate predictions in a fully-optimized computing system. Cross-validation revealed that apart from S, P and B, significant models can be produced for most targeted nutrients (R-square between 40–85%). Further comparison with OFRA field trial database shows that soil nutrients are indeed critical for agricultural development, with Mn, Zn, Al, B and Na, appearing as the most important nutrients for predicting crop yield. A limiting factor for mapping nutrients using the existing point data in Africa appears to be (1) the high spatial clustering of sampling locations, and (2) missing more detailed parent material/geological maps. Logical steps towards improving prediction accuracies include: further collection of input (training) point samples, further harmonization of measurement methods, addition of more detailed covariates specific to Africa, and implementation of a full spatio-temporal statistical modeling framework.
Resilience and Livelihood Benefits of Climate Smart Agroforestry Practices in Semi-arid Tanzania
The agricultural sector in Tanzania is an important driver for economic growth, poverty alleviation, food security and rural development. However, high dependence on rainfall makes the sector vulnerable to the impacts of climate change. Economic losses due to climate change are estimated at US$200 million per year. The scaling up of climate-smart agriculture practices such as agroforestry can reduce such losses, build resilience in the sector, improve productivity and farmer incomes while restoring ecosystem functions that contribute to climate change mitigation. Agroforestry technologies build a healthy agro-ecosystem and foster greater climate resilience of farm households through restoration of land productivity and diversification of production and income options. However, evidenced-based information on the resilience and livelihood benefits of semi-arid agroforestry systems as a climate smart practice is limited.
Comparison of resilience of different plant teams to drought and temperature extremes in Denmark in sole and intercropping systems
Intercropping (IC) can reduce nitrogen fertilizer requirements, supress weeds, and improve crop yields and yield stability. Three field trials were conducted in Denmark in 2018 with intercropping and sole crops (SC) using spring wheat, barley, faba bean and field pea to compare productivity under five fertilizer levels. The trials were carried out using in a split-plot design with four. Anomalous weather during the 2018 cropping season created drought conditions and high temperatures above 31°C. No effect of fertilizer treatment was found, and total dry matter and grain yields were supressed in all systems. Wheat grain yields averaged 2.14 t ha−1 across systems, ranging from 1.58 t ha−1 as a component of the IC to 2.44 t ha−1 as SC, and barley grain yields averaged 2.35 t ha−1. Faba bean yielded 1.78 t ha−1 as SC, but failed in the IC. Pea failed in both systems. Intercropping barley with cover crops had no effect on grain yield or total dry matter. These results suggest that intercropping provided no production advantage during a drought and illuminate the need to continue conducting research and breeding on drought-resistant cultivars.