Rice yield potential, gaps and constraints during the past three decades in a climate-changing Northeast China

Wang, Xiaoyu; Li, Tao; Yang, Xiaoguang; Zhang, Tianyi; Liu, Zhijuan; Guo, Erjing; Liu, Ziqi; Huihui, Qu; Chen, Xi; Wang, Lizhi; Xiang, Hao; Lai, Yongcai

doi:10.1016/j.agrformet.2018.04.023

Cited by 38 publications

(16 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The peak SIF was consistently ranked as the top one factor for predicting the final yield, followed by soil properties across all AEZs except zone IV. Excluding zone I, irrigation ratios were also ranked in the top 10 across AEZs, suggesting that management practices significantly affected maize production in China [62,63]. However, the order of climate variables was varied among AEZs.…”

Section: The Important Factors For Maize Yield Predictionmentioning

confidence: 99%

Combining Optical, Fluorescence, Thermal Satellite, and Environmental Data to Predict County-Level Maize Yield in China Using Machine Learning Approaches

Zhang

Luo

et al. 2019

Remote Sensing

View full text Add to dashboard Cite

Maize is an extremely important grain crop, and the demand has increased sharply throughout the world. China contributes nearly one-fifth of the total production alone with its decreasing arable land. Timely and accurate prediction of maize yield in China is critical for ensuring global food security. Previous studies primarily used either visible or near-infrared (NIR) based vegetation indices (VIs), or climate data, or both to predict crop yield. However, other satellite data from different spectral bands have been underutilized, which contain unique information on crop growth and yield. In addition, although a joint application of multi-source data significantly improves crop yield prediction, the combinations of input variables that could achieve the best results have not been well investigated. Here we integrated optical, fluorescence, thermal satellite, and environmental data to predict county-level maize yield across four agro-ecological zones (AEZs) in China using a regression-based method (LASSO), two machine learning (ML) methods (RF and XGBoost), and deep learning (DL) network (LSTM). The results showed that combining multi-source data explained more than 75% of yield variation. Satellite data at the silking stage contributed more information than other variables, and solar-induced chlorophyll fluorescence (SIF) had an almost equivalent performance with the enhanced vegetation index (EVI) largely due to the low signal to noise ratio and coarse spatial resolution. The extremely high temperature and vapor pressure deficit during the reproductive period were the most important climate variables affecting maize production in China. Soil properties and management factors contained extra information on crop growth conditions that cannot be fully captured by satellite and climate data. We found that ML and DL approaches definitely outperformed regression-based methods, and ML had more computational efficiency and easier generalizations relative to DL. Our study is an important effort to combine multi-source remote sensed and environmental data for large-scale yield prediction. The proposed methodology provides a paradigm for other crop yield predictions and in other regions.

show abstract

Section: The Important Factors For Maize Yield Predictionmentioning

confidence: 99%

Combining Optical, Fluorescence, Thermal Satellite, and Environmental Data to Predict County-Level Maize Yield in China Using Machine Learning Approaches

Zhang

Luo

et al. 2019

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…However, whether changes in cropping systems can take place is still uncertain due to the combinations of various factors, such as economic factors, environmental benefits, and farmer acceptance (Plourde, Pijanowski, & Pekin, 2013; Robinson, Ericksen, Chesterman, & Worden, 2015; Wang, Zhang, & Fu, 2016). Previous studies indicated that climate‐smart management can further improve crop yield in China based on agricultural models (Gao et al., 2019; Sun, Yang, Lin, Sassenrath, & Li, 2018; Wang et al., 2018), and global warming will be beneficial for crop production in China. However, our results indicated that the cropping intensity in China has decreased over the past three decades, and we did not make full use of the advantage of global warming in agricultural production.…”

Section: Discussionmentioning

confidence: 99%

Impacts of global warming on the cropping systems of China under technical improvements from 1961 to 2016

et al. 2021

View full text Add to dashboard Cite

The multiple cropping systems (MCS) have been crucial for China's food security due to its limited arable land and the increased population for hundreds of years. Global warming has significantly affected MCS in China during recent decades. However, whether global warming has influenced the MCS in China under technical improvement is still uncertain and has received great attention. Thus, the current study aims to evaluate the impacts of global warming within the improvements of crop cultivars on MCS in China and analyze the changes in cropland and actual cropping area during the past five decades. Our results showed that the cumulative temperature above 0 °C for the double‐cropping system (DCS) and triple‐cropping system (TCS), respectively, increased by 400 and 100 °C compared to the values in the 1980s. The northern limit of the DCS shifted Southward, while the northern limit of the TCS moved Northward. The cropland of the single‐cropping system (SCS) and TCS increased while the cropland of the DCS decreased. Specifically, the winter wheat (Triticum aestivum L.) area, which represents the DCS in northern China, decreased during the past decades. Similarly, the double‐rice (Oryza sativa L.) cropping system area, which represents the TCS in southern China, decreased as it was partly replaced by single‐rice cropping system. Our study indicated that the cropping intensity in China decreased during past decades, and the full use of MCS will lead to high grain production potential in the transition area. The results will be beneficial for optimizing the cropping distribution across China and enhance the food security.

show abstract

“…There are many biotic and abiotic factors including anthropogenic and natural factors, such as mechanization, variety, irrigation, soil and climate that interact to limit yields and NUE [24,78]. Further understanding of the causes of yield and NUE gaps and constraints on their improvement would require much more precise information on these limitations at different research scales.…”

Section: Analysis Of Limiting Factorsmentioning

confidence: 99%

The Potential for Improving Rice Yield and Nitrogen Use Efficiency in Smallholder Farmers: A Case Study of Jiangsu, China

et al. 2020

View full text Add to dashboard Cite

Closing yield (YG) and nitrogen use efficiency (NUE) gaps amongst smallholder farmers are critical to ensuring food security and environmental sustainability. Here we report a comprehensive analysis of a data set derived from farm-surveys and previously published studies in a typical high N input area of China. Using scenario analysis, farmers from both sources were divided into four rice production levels to assess the YG and NUE of smallholder farmers. Farm surveys showed that rice yield and partial factor productivity of applied N (PFPN) averaged 8273 kg ha−1 and 23.1 kg kg−1 at regional-scale, with a potential increase of 21–43% and 33–52%, respectively. A wide variation in yield and PFPN across different types of farmer was observed. Optimized N management significantly narrowed YGs by 3.7% and PFPN gap by 63.5% on average based on the published literature. Multiple factors, including excessive N rates, small rice planting area (0.33 ha), the aging (51 years old) and low education level (6 years of education) of the major labor force, can partly explain causes of yield and NUE gaps. These findings provide farm-based evidence that centralized management, good agronomy plus advances in knowledge and technologies are essential for future agricultural development.

show abstract

Rice yield potential, gaps and constraints during the past three decades in a climate-changing Northeast China

Cited by 38 publications

References 37 publications

Combining Optical, Fluorescence, Thermal Satellite, and Environmental Data to Predict County-Level Maize Yield in China Using Machine Learning Approaches

Combining Optical, Fluorescence, Thermal Satellite, and Environmental Data to Predict County-Level Maize Yield in China Using Machine Learning Approaches

Impacts of global warming on the cropping systems of China under technical improvements from 1961 to 2016

The Potential for Improving Rice Yield and Nitrogen Use Efficiency in Smallholder Farmers: A Case Study of Jiangsu, China

Contact Info

Product

Resources

About