To meet the challenges of climate change, population growth, and an increasing food demand, an accurate, timely and dynamic yield estimation of regional and global crop yield is critical to food trade and policy-making. In this study, a machine learning method (Random Forest, RF) was used to estimate winter wheat yield in China from 2014 to 2018 by integrating satellite data, climate data, and geographic information. The results show that the yield estimation accuracy of RF is higher than that of the multiple linear regression method. The yield estimation accuracy can be significantly improved by using climate data and geographic information. According to the model results, the estimation accuracy of winter wheat yield increases dramatically and then flattens out over months; it approached the maximum in March, with R² and RMSE reaching 0.87 and 488.59 kg/ha, respectively; this model can achieve a better yield forecasting at a large scale two months in advance.

Carbon dioxide (CO₂) is one of the most significant greenhouse gases, and its concentration and distribution in the atmosphere have always been a research hotspot. To study the temporal and spatial characteristics of atmospheric CO₂ globally, it is crucial to evaluate the consistency of observation data from different carbon observation satellites. This study utilizes data from the Total Carbon Column Observing Network (TCCON) to verify the column-averaged dry air mole fractions of atmospheric CO₂ (XCO₂) retrieved by satellites from October 2014 to May 2016, specifically comparing the XCO₂ distributions from the Greenhouse Gases Observing Satellite (GOSAT) and Orbiting Carbon Observatory 2 (OCO-2). Our analysis indicates a strong correlation between the TCCON and both the GOSAT (correlation coefficient of 0.85) and OCO-2 (correlation coefficient of 0.91). Cross-validation further reveals that the measurements of the GOSAT and OCO-2 are highly consistent, with an average deviation and standard deviation of 0.92 ± 1.16 ppm and a correlation coefficient of 0.92. These differences remain stable over time, indicating that the calibration in the data set is reliable. Moreover, monthly averaged time-series and seasonal climatology comparisons were also performed separately over the six continents, i.e., Asia, North America, Europe, Africa, South America, and Oceania. The investigation of monthly XCO₂ values across continents highlights greater consistency in Asia, North America, and Oceania (standard deviation from 0.15 to 0.27 ppm) as compared to Europe, South America, and Africa (standard deviation from 0.45 to 0.84 ppm). A seasonal analysis exhibited a high level of consistency in spring (correlation coefficient of 0.97), but lower agreement in summer (correlation coefficient of 0.78), potentially due to cloud cover and aerosol interference. Although some differences exist among the datasets, the overall findings demonstrate a strong correlation between the satellite measurements of XCO₂. These results emphasize the importance of continued monitoring and calibration efforts to ensure the accurate assessment and understanding of atmospheric CO₂ levels.

As a highly variable factor, climate plays a crucial role in winter wheat production. Quantifying its impact on crop yield and determining its relative importance is essential. This study uses the Random Forest (RF) algorithm to evaluate the effects of climate change on winter wheat yields in the North China Plain (1980–2020) and assess yield sensitivity to various climate indicators. The results show that the RF model performs well in simulating winter wheat yields across planting regions, with RRMSE values ranging from 12.88% to 22.06%, Spearman’s r from 0.84 to 0.91, and R² from 0.69 to 0.83. From 1980 to 2020, climate trends negatively affected winter wheat yields in Beijing, Tianjin, Hebei, Shanxi, and Jiangsu while promoting yield increases in Henan and Anhui. In general, a 10% increase in precipitation tends to enhance yields, except in northern Hebei, northern Shanxi, and Jiangsu. A 10% rise in solar radiation benefits most regions, although it leads to yield reductions in some areas of Anhui and Jiangsu. A 1 °C increase in temperature typically results in yield decreases, except in Beijing, southern Hebei, and parts of Shanxi and Henan. Among the three predictors, temperature is the most influential (33.81–44.19%), followed by solar radiation (29.01–37.47%) and precipitation (23.27–30.88%). These findings highlight the need for temperature-focused management strategies and region-specific approaches to optimize wheat yields and ensure sustainable production under climate change.

Heat stress will restrict rice yield in the middle and lower reaches of the Yangtze River. An understanding of the meteorological conditions of heat stress of rice production is important for improving the accuracy of the phenology simulation. Based on the observations of phenology and heat stress of rice agrometeorological stations in this region, as well as meteorological observations and future scenarios, this study analyzed the spatiotemporal change of heat stress and its impacts on rice growth in this region from 1990 to 2009. The results showed that the heat stress frequency of early rice increased in this region from 2000 to 2009, and that of late rice and single-season rice decreased. Moreover, rice phenology will advance under heat stress conditions. The spatiotemporal consistency of the observations and the meteorological index of heat stress shows that the change in heat stress is attributed to climate changes and extreme meteorological events. Under future climate scenarios, it is found that the frequency of heat stress will increase, which will have a serious impact on rice production. The results suggest that positive and effective measures should be taken to adapt to climate change for rice production.