Predicting crop yields, and especially anomalously low yields, is of special importance for food insecure countries. In this study, we investigate a flexible deep learning approach to forecast crop yield at the provincial administrative level based on deep 1D and 2D convolutional neural networks using limited data. This approach meets the operational requirements—public and global records of satellite data in an application ready format with near real time updates—and can be transferred to any country with reliable yield statistics. Three-dimensional histograms of normalized difference vegetation index (NDVI) and climate data are used as input to the 2D model, while simple administrative-level time series averages of NDVI and climate data to the 1D model. The best model architecture is automatically identified during efficient and extensive hyperparameter optimization. To demonstrate the relevance of this approach, we hindcast (2002–2018) the yields of Algeria’s three main crops (barley, durum and soft wheat) and contrast the model’s performance with machine learning algorithms and conventional benchmark models used in a previous study. Simple benchmarks such as peak NDVI remained challenging to outperform while machine learning models were superior to deep learning models for all forecasting months and all tested crops. We attribute the poor performance of deep learning to the small size of the dataset available.
The droughts that hit North and North Western Europe in 2018 and 2019 served as a wake-up call that temperate regions are also affected by these kinds of slow progressing or creeping disasters. Long-term drivers, such as land-use changes, may have exacerbated the impacts of these meteorological droughts. These changes, which are spread over a long time span, may even be difficult to perceive for an individual, but make a big difference in how these rare weather events impact a region. In this paper, we introduce three long-term drivers: forest fires in Europe, global urbanisation, and global deforestation. We attempt to provide a first assessment of their trends, mainly using statistics derived from satellite imagery published in recent literature. Due to the complexity of drought impacts, and the scarcity of quantitative impact data, the relationship between drought impact and these three processes for land use change is difficult to quantify; however, hence we present a survey of the recent trends in these land use change processes and the possible mechanics by which they affect drought impacts. Based on this survey we can conclude that the extent and the number of wildfires have increased markedly in Europe since 2010. Deforestation is still occurring in the tropics, with a loss of 12% in the last 30 years but has halted in the northern regions. Urbanisation has more than doubled in the same time span in the tropics and subtropics, mostly at the expense of forests, while in Europe urbanisation took place mainly in the northern part of the continent. We can conclude that none of these implicit drought drivers followed a favourable trend in the last 30 years. With consistent and worldwide monitoring, for example, by using satellite imagery, we can regularly inform the scientific community on the trends in these drought impact affecting processes, thus helping decision makers to understand how far we have progressed in making the world resilient to drought impacts.
Accurate and timely crop yield forecasts are crucial for guiding decisions on resource allocation, market strategies, and food security interventions, especially in food-insecure regions. These forecasts enable policymakers and stakeholders in the global food supply chain to anticipate production levels and implement effective mitigation and response measures. As the complexity of data and the need for precise predictions continue to grow, there is an increasing demand for models that can efficiently process and analyze diverse datasets. To address these challenges, we present an application of a foundation model for small- to medium-sized tabular data (TabPFN), to sub-national yield forecasting task in South Africa for maize, soybeans and sunflowers. We used the dekadal (10-day) time series of Earth Observation (EO; FAPAR and soil moisture) and gridded weather data (air temperature, precipitation and radiation) to forecast the yield of summer crops at the sub-national level. The crop yield data were available for 23 years and for up to 8 provinces. Covariate variables for TabPFN (i.e., EO and weather) were extracted by region and aggregated at a monthly scale. We benchmarked the results of the TabPFN against six ML models and two baseline models. Leave-one-year-out cross-validation experiment setting was used in order to ensure the assessment of the model’s capacity to forecast an unseen year. Results showed that TabPFN and ML models exhibit comparable accuracy, both outperforming the baseline approaches. For maize, the best-performing ML model achieved 6.8% rRMSEp, while TabPFN achieved 8.8%, with R² of 0.91 and 0.86 respectively at the national level. Nonetheless, TabPFN demonstrated practical utility due to its faster tuning time and reduced requirement for feature engineering.