A multidisciplinary journal that focuses on public health and technology, public health informatics, mass media campaigns, surveillance, and innovation in public health practice and research. Also dedicated to rapid open data sharing during epidemics.

Crop yield prediction before the harvest is crucial for food security, grain trade, and policy making. Previously, several machine learning methods have been applied to predict crop yield using different types of variables. In this study, we propose using the Geographically Weighted Random Forest Regression (GWRFR) approach to improve crop yield prediction at the county level in the US Corn Belt. We trained the GWRFR and five other popular machine learning algorithms (Multiple Linear Regression (MLR), Partial Least Square Regression (PLSR), Support Vector Regression (SVR), Decision Tree Regression (DTR), and Random Forest Regression (RFR)) with the following different sets of features: (1) full length features; (2) vegetation indices; (3) gross primary production (GPP); (4) climate data; and (5) soil data. We compared the results of the GWRFR with those of the other five models. The results show that the GWRFR with full length features (R² = 0.90 and RMSE = 0.764 MT/ha) outperforms other machine learning algorithms. For individual categories of features such as GPP, vegetation indices, climate, and soil features, the GWRFR also outperforms other models. The Moran’s I value of the residuals generated by GWRFR is smaller than that of other models, which shows that GWRFR can better address the spatial non-stationarity issue. The proposed method in this article can also be potentially used to improve yield prediction for other types of crops in other regions.

Monoculture and simplified two-crop rotation systems compromise the ecosystem services essential to crop production, diminish agricultural productivity, and cause detrimental effects on the environment. In contrast to the simplified two-crop rotation, diversified crop rotation (DCR) refers to rotation systems that contain three or more crops. Despite multiple benefits generated by DCR, its usage has dwindled over the past several decades. This paper examined determinants of farmers' adoption decisions and perceived benefits of DCR in the west margins of the U.S. Corn Belt where crop diversity has declined. We analyzed 708 farmer responses from a farmer survey conducted in the eastern South Dakota in 2018, accounting for county-level climate variables, as well as cropland data, soil and topographic variables in close proximity of the farm. Our findings indicated that farmers were more likely to utilize DCR as an adaptive strategy to cope with water deficit and reduce soil erosion on marginal land. Additionally, livestock integration and organic farming helped necessitate DCR adoption and magnify its benefits. Producer concerns towards lack of equipment and new crop profitability diluted producers' interests in DCR practice and compromised its benefits. Enhanced technical and policy support, along with infrastructure and market development, could help producers fully utilize DCR benefits and expand DCR usage to more regions.

Climate variability and trends have significant environmental and socioeconomic impacts. Global challenges such as food security, biodiversity loss, water scarcity and human health are affected by reference evapotranspiration, temperature, solar radiation, and precipitation together, but nonlinear dynamics of these four climatic factors have not been assessed simultaneously at the national scale. This leads to unclear climatic dynamics and limited applications. To address this knowledge gap, we analyzed the daily variability and trends of four climatic factors (reference evapotranspiration, temperature, solar radiation, and precipitation) in China simultaneously using high spatial resolution data from 1960 to 2013. The results indicate that the daily variability of climate system dynamics (quantified by multiplying fractal dimensions of the four climatic factors) in north China was higher than that in south China. For example, the climate system dynamics were more chaotic and with higher nonlinear variation in north China, most notably in Heilongjiang Province, the major grain base of China, posing threats to food security in the context of growing national population. Spatial distribution of variability varies among different climatic factors. Our study highlights the need for a more holistic study of climate variability and trends in other countries with multiple climate types to address challenges of sustainable development.