Accurate crop yield assessments using satellite remote sensing-based methods are of interest for regional monitoring and the design of policies that promote agricultural resiliency and food security. However, the application of current vegetation productivity algorithms derived from global satellite observations is generally too coarse to capture cropland heterogeneity. The fusion of data from different sensors can provide enhanced information and overcome many of the limitations of individual sensors. In thitables study, we estimate annual crop yields for seven important crop types across Montana in the continental USA from 2008–2015, including alfalfa, barley, maize, peas, durum wheat, spring wheat and winter wheat. We used a satellite data-driven light use efficiency (LUE) model to estimate gross primary productivity (GPP) over croplands at 30-m spatial resolution and eight-day time steps using a fused NDVI dataset constructed by blending Landsat (5 or 7) and Terra MODIS reflectance data. The fused 30-m NDVI record showed good consistency with the original Landsat and MODIS data, but provides better spatiotemporal delineations of cropland vegetation growth. Crop yields were estimated at 30-m resolution as the product of estimated GPP accumulated over the growing season and a crop-specific harvest index (HI_GPP). The resulting GPP estimates capture characteristic cropland productivity patterns and seasonal variations, while the estimated annual crop production results correspond favorably with reported county-level crop production data (r = 0.96, relative RMSE = 37.0%, p < 0.05) from the U.S. Department of Agriculture (USDA). The performance of estimated crop yields at a finer (field) scale was generally lower, but still meaningful (r = 0.42, relative RMSE = 50.8%, p < 0.05). Our methods and results are suitable for operational applications of crop yield monitoring at regional scales, suggesting the potential of using global satellite observations to improve agricultural management, policy decisions and regional/global food security.

In response to global calls for sustainable food production, we identify two diverging paradigms to address the future of agriculture. We explore the possibility of uniting these two seemingly diverging paradigms of production-oriented and ecologically oriented agriculture in the form of precision agroecology. Merging precision agriculture technology and agroecological principles offers a unique array of solutions driven by data collection, experimentation, and decision support tools. We show how the synthesis of precision technology and agroecological principles results in a new agriculture that can be transformative by (1) reducing inputs with optimized prescriptions, (2) substituting sustainable inputs by using site-specific variable rate technology, (3) incorporating beneficial biodiversity into agroecosystems with precision conservation technology, (4) reconnecting producers and consumers through value-based food chains, and (5) building a just and equitable global food system informed by data-driven food policy. As a result, precision agroecology provides a unique opportunity to synthesize traditional knowledge and novel technology to transform food systems. In doing so, precision agroecology can offer solutions to agriculture’s biggest challenges in achieving sustainability in a major state of global change.

Modern weed science is at a crossroads. Born out of advances in chemistry, it has focused on minimizing weed competition with genetically uniform crops and heavy reliance on herbicides. Paradoxically, the success obtained with such an approach and the reluctance to conduct integrated and multidisciplinary research has resulted in unintended, but predictable, consequences, including the selection of herbicide resistant biotypes. Advances in eco-evolutionary biology, a relatively recent discipline that seeks to understand how local population dynamics arise from phenotypic variation resulting from natural selection, habitat distribution, and propagule dispersal across the landscape are transforming our understanding of the processes that regulate agroecosystems. Within this framework, complementary tactics to develop alternative weed management programs include the following: (1) weed scientists must recognize that evolution occurs within crop fields at ecologically-relevant time scales and is rooted in the inherent variation that exists in all populations; (2) weed management should recognize that the probability of a resistant mutant is directly related to the population size; (3) farmers need to acknowledge that herbicide resistance transcends any one farm and should coordinate local practices with regional actions; (4) incentives should be developed and implemented to help the adoption of eco-evolutionary management programs; and (5) risk analysis can help incorporate an eco-evolutionary perspective into integrated weed management programs.

In recent years, the use of remotely sensed and on-ground observations of crop fields, in conjunction with machine learning techniques, has led to highly accurate crop yield estimations. In this work, we propose to further improve the yield prediction task by using Convolutional Neural Networks (CNNs) given their unique ability to exploit the spatial information of small regions of the field. We present a novel CNN architecture called Hyper3DNetReg that takes in a multi-channel input raster and, unlike previous approaches, outputs a two-dimensional raster, where each output pixel represents the predicted yield value of the corresponding input pixel. Our proposed method then generates a yield prediction map by aggregating the overlapping yield prediction patches obtained throughout the field. Our data consist of a set of eight rasterized remotely-sensed features: nitrogen rate applied, precipitation, slope, elevation, topographic position index (TPI), aspect, and two radar backscatter coefficients acquired from the Sentinel-1 satellites. We use data collected during the early stage of the winter wheat growing season (March) to predict yield values during the harvest season (August). We present leave-one-out cross-validation experiments for rain-fed winter wheat over four fields and show that our proposed methodology produces better predictions than five compared methods, including Bayesian multiple linear regression, standard multiple linear regression, random forest, an ensemble of feedforward networks using AdaBoost, a stacked autoencoder, and two other CNN architectures.