Search

A timely and accurately predicted grain yield can ensure regional and global food security. The scientific community is gradually advancing the prediction of regional-scale maize yield. However, the combination of various datasets while predicting the regional-scale maize yield using simple and accurate methods is still relatively rare. Here, we have used multi-source datasets (climate dataset, satellite dataset, and soil dataset), lasso algorithm, and machine learning methods (random forest, support vector, extreme gradient boosting, BP neural network, long short-term memory network, and K-nearest neighbor regression) to predict China's county-level maize yield. The use of multi-sourced datasets advanced the predicting accuracy of maize yield significantly compared to the single-sourced dataset. We found that the machine learning methods were superior to the lasso algorithm, while random forest, extreme gradient boosting, and support vector machine represented the most preferable methods for maize yield prediction in China (R2 ≥ 0.75, RMSE = 824–875 kg/ha, MAE = 626–651 kg/ha). The climate dataset contributed more to the prediction of maize yield, while the satellite dataset contributed to tracking the maize growth process. However, the methods' accuracies and the dominant variables affecting maize growth varied with agricultural regions across different geographic locations. Our research serves as an important effort to examine the feasibility of multi-source datasets and machine learning techniques for regional-scale maize yield prediction. In addition, the methodology we have proposed here provides guidance for reliable yield prediction of different crops. [ABSTRACT FROM AUTHOR]

Reliable projections of monsoon mean and extreme precipitation are vital to water resource management, disaster mitigation as well as policy makings. Since the climate models have better capability in projecting mean precipitation, the relationship between mean and extreme precipitation is a crucial clue for reliable projections of extreme precipitation. However, selections of optimal models in reproducing historical mean/extreme precipitation and their relationship were rarely reported. Here, more credible projections of mean/extreme precipitation and their connections over Northern Hemisphere land monsoon domain (NHLMD) were explored after a systematical assessment of the models from Coupled Model Intercomparsion Project Phase 6 (CMIP6) and CMIP5. Results indicated that most models could well reproduce the climatology and the variation of mean precipitation over NHLMD, while large portions have underestimated the extreme precipitation threshold (EPTH) and overestimated the extreme precipitation days (EPDs). However, nearly all models captured the observed robust relationships between mean and extreme precipitation. The projected mean precipitation and EPDs exhibit coherent variations with increase trend over Asian‐North African monsoon, and decrease trend over North American monsoon. The significant positive correlations between mean precipitation and EPDs will continue during 21st century. Considering the relatively low skills and large uncertainty in the simulation and the projection of EPDs, the tight connection could be used to reliably project the future extreme precipitation over the NHLMD using the projection of monsoon mean precipitation via the selected models. [ABSTRACT FROM AUTHOR]

Future global temperature change will have significant effects on society and ecosystems. Earth system models (ESM) are the primary tools to explore future climate change. However, ESMs have great uncertainty and often run at a coarse spatial resolution (usually about 2°). Accurate high‐spatial‐resolution temperature dataset are needed to improve our understanding of temperature variations and for many other applications. We apply Super resolution (SR) in computer vision using deep learning (DL) to merge 31 ESMs data. The proposed method performs data merging, bias‐correction, and spatial downscaling simultaneously. The CRU TS (Climate Research Unit gridded Time Series) data is used as reference data in the model training process. To find a suitable DL method, we select five SR methodologies with different structures. We compare the performances of the methods based on mean square error (MSE), mean absolute error (MAE) and Pearson correlation coefficient (R). The best method is used to merge the projected monthly data (1850–1900), and monthly future scenarios data (2015–2100), at the high spatial resolution of 0.5°. Results show that the merged data have considerably improved performance compared with individual ESM data and their ensemble mean (EM), both spatially and temporally. The MAE shows significant improvement; the spatial distribution of the MAE widens along the latitudes in the Northern Hemisphere. The MAE of merged data is ranging from 0.60 to 1.50, the South American (SA) has the lowest error and the Europe has the highest error. The merged product has excellent performance when the observation data is smooth with few fluctuations in the time series. This work demonstrates the applicability and effectiveness of the DL methods in data merging, bias‐correction and spatial downscaling when enough training data are available. Data can be accessed at https://doi.org/10.5281/zenodo.5746632. [ABSTRACT FROM AUTHOR]