A5088794531- Rice Cultivation and Yield Improvement
- Remote Sensing in Agriculture
- Climate change impacts on agriculture
- Land Use and Ecosystem Services
- Remote Sensing and Land Use
- Nutritional Studies and Diet
- Soybean genetics and cultivation
- Nutrition, Genetics, and Disease
- Flood Risk Assessment and Management
- Plant responses to elevated CO2
- Obesity, Physical Activity, Diet
- Hydrology and Drought Analysis
- Leaf Properties and Growth Measurement
- Crop Yield and Soil Fertility
- GABA and Rice Research
- Nutrition, Health and Food Behavior
- Agriculture Sustainability and Environmental Impact
Beijing Normal University
2022-2024
Abstract. Rice is the most important staple food in Asia. However, high-spatiotemporal-resolution rice yield datasets are limited over this large region. The lack of such products greatly hinders studies that aimed at accurately assessing impacts climate change and simulating agricultural production. Based on annual maps Asia, we incorporated multisource predictors into three machine learning (ML) models to generate a high-spatial-resolution (4 km) seasonal dataset (AsiaRiceYield4km) for...
Abstract. Soybean, an essential food crop, has witnessed a steady rise in demand recent years. There is lack of high-resolution annual maps depicting soybean-planting areas China, despite China being the world's largest consumer and fourth-largest producer soybean. To address this gap, we developed novel Regional Adaptation Spectra-Phenology Integration method (RASP) based on Sentinel-2 remote sensing images from Google Earth Engine (GEE) platform. We utilized various auxiliary data (e.g.,...
Abstract. Soybean, an essential food crop, has witnessed a steady rise in demand recent years. There is lack of high-resolution annual maps depicting soybean planting areas China, despite China being the world’s largest consumer and fourth producer soybeans. To address this gap, we developed novel method called phenological- pixel-based area mapping (PPS) based on Sentinel-2 remote sensing images from Google Earth Engine (GEE) platform. We utilized various auxiliary data (e.g., cropland...
CONTEXTCrop phenology is a critical ecological indicator reflecting climate change impact on agricultural systems. As one of the most important economic crops in China, investigating dynamics and drivers soybean essential for developing adaptation options.OBJECTIVEThe objectives are to investigate trends soybeans key phenological stages growth periods across China from 1981 2020; understand their responses various climatic factors; disentangle contributions different anthropogenic factors...
Abstract. Rice is the most important staple food in Asia. However, high-spatiotemporal-resolution rice yield datasets are very limited over a large region. The lack of such products hugely hinders studies on accurately assessing impacts climate change and simulating agricultural production. Based dynamic maps Asia, we incorporated four predictor categories into three machine learning (ML) models to generate high-spatial-resolution (4 km) dataset (AsiaRiceYield4km) for main seasons from 1995...
With China's rapid economic growth, eating away from home (EAFH) has surged. The absence of EAFH data leads to significant underestimation household food consumption. We utilized the China Health and Nutrition Survey (CHNS), a comprehensive survey construct models (R2 = 0.67) for major types estimate consumption 2000 2020. By 2020, daily averaged 214g in urban 84g rural areas, accounting 17.6% 7.8% total, respectively. grew both rate was slower than at (EAH). Food’s positive effects on...
The planting area of three staple crops (rice, maize and wheat) in China ranks among the highest world. Developing maps consistent with county-level statistical data for agricultural policy formulation disaster risk prevention. However, there is a scarcity available datasets these China, existing public limited only few years, often exhibit significant disparities from data. This dataset was established using crop mapping method based on multi-source Firstly, we determined rough spatial...
Tuning hyper-parameters is helpful to improve ML prediction accuracy (Shahhosseini et al., 2021).Here, the grid search method was used find optimal parameter combinations.Three of RF were tuned: 'n_estimators', 'max_features', and 'min_samples_split', six for XGBoost: 'max_depth', 'min_child_weight', 'eta', 'gamma', 'tree_method'.For LSTM, dropout rate set as 0.2 L2 regularization reduce over-fitting.Besides, early stopping patience 50 further over-fitting.The hyper-parameter through...