Forecasting crop yields is becoming increasingly important under the current context in which food security needs to be ensured despite the challenges brought by climate change, an expanding world population accompanied by rising incomes, increasing soil erosion, and decreasing water resources. Temperature, radiation, water availability and other environmental conditions influence crop growth, development, and final grain yield in a complex nonlinear manner. Machine learning (ML) techniques, and deep learning (DL) methods in particular, can account for such nonlinear relations between yield and its covariates. However, they typically lack transparency and interpretability, since the way the predictions are derived is not directly evident. Yet, in the context of yield forecasting, understanding which are the underlying factors behind both a predicted loss or gain is of great relevance. Here, we explore how to benefit from the increased predictive performance of DL methods while maintaining the ability to interpret how the models achieve their results. To do so, we applied a deep neural network to multivariate time series of vegetation and meteorological data to estimate the wheat yield in the Indian Wheat Belt. Then, we visualized and analyzed the features and yield drivers learned by the model with the use of regression activation maps. The DL model outperformed other tested models (ridge regression and random forest) and facilitated the interpretation of variables and processes that lead to yield variability. The learned features were mostly related to the length of the growing season, and temperature and light conditions during this time. For example, our results showed that high yields in 2012 were associated with low temperatures accompanied by sunny conditions during the growing period. The proposed methodology can be used for other crops and regions in order to facilitate application of DL models in agriculture.

Studying phytoplankton functional types (PFTs) from space is possible due to recent advances in remote sensing. Though a variety of products are available, the limited number of wavelengths available compared to the number of model parameters needed to be retrieved is still a major problem in using ocean-color data for PFT retrievals. Here, we investigated which band placement could improve retrievals of three particular PFTs (diatoms, coccolithophores and cyanobacteria). In addition to analyzing dominant spectral features in the absorption spectra of the target PFTs, two previously-developed methods using measured spectra were applied to simulated data. Such a synthetic dataset allowed for significantly increasing the number of scenarios and enabled a full control over parameters causing spectral changes. We evaluated the chosen band placement by applying an adapted ocean reflectance inversion, as utilized in the generalized inherent optical properties (GIOP) retrieval. Results show that the optimal band settings depend on the method applied to determine the bands placement, as well as on the internal variability of the dataset investigated. Therefore, continuous hyperspectral instruments would be most beneficial for discriminating multiple PFTs, though a small improvement in spectral sampling and resolution does not significantly modify the results. Bands, which could be added to future instruments (e.g., Ocean and Land Colour Instrument (OLCI) instrument on the upcoming Sentinel-3B,-3C,-3D, etc., and further satellites) in order to enhance PFT retrieval capabilities, were also determined.

Estimating crop yields is becoming increasingly relevant under the current context of an expanding world population accompanied by rising incomes in a changing climate. Crop growth, crop development, and final grain yield are all determined by environmental conditions in a complex nonlinear manner. Machine learning (ML), and deep learning (DL) methods in particular, can account for such nonlinear relations between yield and its drivers. However, they typically lack transparency and interpretability, which in the context of yield forecasting is of great relevance. Here, we explore how to benefit from the increased predictive performance of DL methods without compromising the ability to interpret how the models achieve their results for an example of the wheat yield in the Indian Wheat Belt.We applied a convolutional neural network to multivariate time series of meteorological and satellite-derived vegetation variables at a daily resolution to estimate the wheat yield in the Indian Wheat Belt. Afterwards, the features and yield drivers learned by the model were visualized and analyzed with the use of regression activation maps. The learned features were primarily related to the length of the growing season, temperature, and light conditions during the growing season. Our analysis showed that high yields in 2012 were associated with low temperatures accompanied by sunny conditions during the growing period. The proposed methodology can be used for other crops and regions in order to facilitate application of DL models in agriculture. References:Wolanin A., Mateo-Garcı́a G., Camps-Valls G., Gómez-Chova L. ,Meroni, M., Duveiller, G., You, L., Guanter L. (2020) Estimating and Understanding Crop Yields with Explainable Deep Learning in the Indian Wheat Belt. Environmental Research Letters.