Along with climate warming, extreme heat events have become more frequent, severe, and seriously threaten rice production. Precisely evaluating rice heat levels based on heat duration and a cumulative intensity index dominated by temperature and humidity is of great merit to effectively assess regional heat risk and minimize the deleterious impact of rice heat along the middle and lower reaches of the Yangtze River (MLRYR). This study quantified the response mechanism of daytime heat accumulation, night-time temperature, and relative humidity to disaster-causing intensity in three categories of single-season rice heat (dry, medium, and wet conditions) using Fisher discriminant analysis to obtain the Heat Comprehensive Intensity Index daily (HCIId). It is indicated that relative humidity exhibited a negative contribution under dry heat, i.e., heat disaster-causing intensity increased with decreasing relative humidity, with the opposite being true for medium and wet heat. The Kappa coefficient, combined with heat duration and cumulative HCIId, was implemented to determine classification thresholds for different disaster levels (mild, moderate, and severe) to construct heat evaluation levels. Afterwards, spatiotemporal changes in heat risk for single-season rice through the periods of 1986–2005, 2046–2065 and 2080–2099 under SSP2-4.5 and SSP5-8.5 were evaluated using climate scenario datasets and heat evaluation levels carefully constructed. Regional risk projection explicitly revealed that future risk would reach its maximum at booting and flowering, followed by the tillering stage, and its minimum at filling. The future heat risk for single-season rice significantly increased under SSP5-8.5 than SSP2-4.5 in MLRYR. The higher risk would be highlighted in eastern Hubei, eastern Hunan, most of Jiangxi, and northern Anhui. As time goes on, the heat risk for single-season rice in eastern Jiangsu and southern Zhejiang will progressively shift from low to mid-high by the end of the twenty-first century. Understanding the potential risk of heat exposure at different growth stages can help decision-makers guide the implementation of targeted measures to address climate change. The proposed methodology also provides the possibility of assessing other crops exposure to heat stress or other extreme events.

Droughts, intensified by climate change and human activities, pose a significant threat to winter wheat cultivation in the Huang-Huai-Hai (HHH) region. Soil moisture drought indices are crucial for monitoring agricultural droughts, while challenges such as data accessibility and soil heterogeneous necessitate the use of numerical simulations for their effective regional-scale applications. The existing simulation methods like physical process models and machine learning (ML) algorithms have limitations: physical models struggle with parameter acquisition at regional scales, while ML algorithms face difficulties in agricultural settings due to the presence of crops. As a more advanced and complex branch of ML, deep learning algorithms face even greater limitations related to crop growth and agricultural management. To address these challenges, this study proposed a novel hybrid monitoring system that merged ML algorithms with a physical process model. Initially, we employed the Random Forest (RF) regression model that integrated multi-source environmental factors to estimate soil moisture prior to the sowing of winter wheat, achieving an average coefficient of determination (R²) of 0.8618, root mean square error (RMSE) of 0.0182 m³ m⁻³, and mean absolute error (MAE) of 0.0148 m³ m⁻³ across eight soil depths. The RF regression models provided vital parameters for the operation of the Water Balance model for Winter Wheat (WBWW) at a regional scale, enabling effective drought monitoring and assessments combined with the Soil Moisture Anomaly Percentage Index (SMAPI). Subsequent comparative analyses between the monitoring system-generated results and the actual disaster records during two regional-scale drought events highlighted its efficacy. Finally, we utilized this monitoring system to examine the spatiotemporal variations in drought patterns in the HHH region over the past two decades. The findings revealed an overall intensification of drought conditions in winter wheat, with a decline in average SMAPI at a rate of −0.021% per year. Concurrently, there has been a significant shift in drought patterns, characterized by an increase in both the frequency and extremity of drought events, while the duration and intensity of individual drought events have decreased in a majority of the HHH region. Additionally, we identified the northeastern, western, and southern areas of HHH as areas requiring concentrated attention and targeted intervention strategies. These efforts signify a notable application of multi-source data fusion techniques and the integration of physical process models within a big data context, thereby facilitating effective drought prevention, agricultural management, and mitigation strategies.

This study aimed to investigate the impact of low-temperature (LT) stress during the jointing stage on three most representative wheat varieties in the Huang-Huai-Hai region: “Shannong 38” (a robust winter wheat variety), “Jimai 22” (a semi-winter wheat variety), and “Zhenmai 12” (a weak winter wheat variety). The objective was to explain the sensitivity and change thresholds of various physiological and yield indicators of three winter wheat varieties to low temperatures during the jointing stage and to construct an index for the grading of LT disasters during the jointing stage using principal component analysis. Controlled environment experiments were conducted using an artificial climate chamber during the jointing stage of winter wheat. Five daily minimum temperature treatments were applied, namely (T1, −6 °C); (T2, −3 °C); (T3, 0 °C); (T4, 3 °C); (T5, 6 °C); and control (CK, 8 °C). The duration of treatments was divided into three levels: (D1: 2 days), (D2: 4 days), and (D3: 6 days). It was found that the photosynthetic parameters and chlorophyll content showed a decreasing trend with the increase in the degree of LT stress. The activities of protective enzymes and endogenous hormones increased during the early stages of LT stress or at relatively high temperatures. However, they decreased significantly with an increase in LT stress. Among the varieties, “Zhenmai 12” exhibited a yield reduction rate exceeding 10% under 3 °C LT stress for more than 4 days and a yield reduction rate exceeding 20% under 0 °C LT stress for more than 6 days. “Jimai 22” showed a yield reduction rate exceeding 10% under 3 °C LT stress lasting more than 2 days, and a yield reduction rate exceeding 20% under −3 °C LT stress lasting more than 4 days. “Shannong 38” experienced a yield reduction rate exceeding 10% under 0 °C LT stress lasting more than 4 days and a yield reduction rate exceeding 20% under −6 °C LT stress lasting more than 6 days. Principal component analysis (PCA) conducted on all trait indicators of the three winter wheat varieties revealed that “Zhenmai 12” experienced mild LT stress at 6 °C for 2 days, moderate LT stress at 0 °C for 6 days, and severe LT stress at −3 °C for 6 days. “Jimai 22” experienced mild LT stress under 6 °C for 6 days, moderate LT stress under 0 °C for 4 days, and severe LT stress under −6 °C for 2 days. “Shannong 38” experienced mild LT stress under 3 °C for 4 days, moderate LT stress under 0 °C for 4 days, and severe LT stress under −6 °C for 6 days.

The implementation of real-time dynamic monitoring of disaster formation and severity is essential for the timely adoption of disaster prevention and mitigation measures, which in turn minimizes disaster-related losses and safeguards agricultural production safety. This study establishes a low-temperature disaster (LTD) monitoring system based on machine learning algorithms, which primarily consists of a module for identifying types of disasters and a module for simulating the evolution of LTDs. This study firstly employed the KNN model combined with a piecewise function to determine the daily dynamic minimum critical temperature for low-temperature stress (LTS) experienced by winter wheat in the Huang-Huai-Hai (HHH) region after regreening, with the fitting model’s R², RMSE, MAE, NRMSE, and MBE values being 0.95, 0.79, 0.53, 0.13, and 1.716 × 10⁻¹¹, respectively. This model serves as the foundation for determining the process by which winter wheat is subjected to LTS. Subsequently, using the XGBoost algorithm to analyze the differences between spring frost and cold damage patterns, a model for identifying types of spring LTDs was developed. The validation accuracy of the model reached 86.67%. In the development of the module simulating the evolution of LTDs, the XGBoost algorithm was initially employed to construct the Low-Temperature Disaster Index (LTDI), facilitating the daily identification of LTD occurrences. Subsequently, the Low-Temperature Disaster Process Accumulation Index (LDPI) is utilized to quantify the severity of the disaster. Validation results indicate that 79.81% of the test set samples exhibit a severity level consistent with historical records. An analysis of the environmental stress-mitigation mechanisms of LTDs reveals that cooling induced by cold air passage and ground radiation are the primary stress mechanisms in the formation of LTDs. In contrast, the release of latent heat from water vapor upon cooling and the transfer of sensible heat from soil moisture serve as the principal mitigation mechanisms. In summary, the developed monitoring framework for LTDs, based on environmental patterns of LTD formation, demonstrates strong generalization capabilities in the HHH region, enabling daily dynamic assessments of the evolution and severity of LTDs.

The accurate and sub-daily identification of agricultural low-temperature disasters (LTDs) facilitates the understanding of their dynamic evolution, the evaluation of the characteristics of disaster events, and informs effective strategies aimed at disaster prevention and mitigation. In order to ensure the timely, precise, and comprehensive capture of disaster processes, we have developed a dynamic evaluation framework for winter wheat spring LTD in the Huang-Huai-Hai (HHH) region, driven by meteorological data. This framework consists of two primary components: a disaster classification module and a dynamic simulation-assessment module. Through disaster mechanisms and comprehensive statistical analysis, we have established the input features and structural framework of the classification module using a decision tree algorithm. The dynamic simulation evaluation module is based on our newly developed index for the cumulative hourly intensity of low-temperature stress (CHI) and its grade indicators. This index integrates the interaction between cold stress (low-temperature intensity, cooling amplitude, and duration) and mitigating conditions (air humidity) during the evolution process of LTD. Based on CHI, we found that as the intensity of low temperatures and the amplitude of cooling rise, along with an extended duration of stress and a reduction in relative humidity, the severity of spring LTDs in winter wheat get worse. The overall validation accuracy of the evaluation framework is 92.6%. High validation accuracy indicates that our newly established framework demonstrates significant efficacy in identifying LTDs and assessing grade. Through the analysis of the characteristics of the disaster process, spring LTDs affecting winter wheat are mainly mild, with frost identified as the primary category of LTD. The duration of freeze injury typically exceeds 24 h, while the duration of frost damage and cold damage is less than 24 h. From 1980 to 2022 in the HHH region, the frequency of spring freeze injury and frost damage on winter wheat showed an overall decreasing trend, with a particularly significant decrease in frost damage occurrences. Conversely, cold damage occurrences are on the rise. In addition, the duration of individual disaster events for the three categories of spring LTDs is decreasing, while both the average intensity and extremity of these events show increasing trends. This study has important practical value for the sub-daily scale evaluation of the spring LTD affecting winter wheat in the HHH region and serves as an effective guide for agricultural disaster prevention and mitigation, as well as for the formulation of planting strategies.

As global warming continues, heat stress events are expected to increase and negatively affect rice production. Spatiotemporal changes in single-season rice exposure to heat stress were explored along the middle and lower reaches of the Yangtze River (MLRYR) in China during 1971–2020 based on created heat thresholds in different phenological stages, derived from comparison of historical heat records for single-season rice and agro-meteorological data. The feature importance (IF) provided by the Random Forest model was used to modulate the relationship between threshold accumulated temperature and yield reduction rate caused by heat stress. In addition, critical temperature thresholds at different phenological stages were determined by combining Overall Accuracy and the Receiver Operating Characteristic (ROC) curve. According to historical disaster records, the heat stress occurred before the reproductive phase (i.e., the tillering–jointing stage) and ended in the filling stage. Critical temperature thresholds of T_max at tillering–jointing, booting, flowering and filling were quantified as 36, 35, 35 and 38 °C, with higher IF values of 13.14, 10.93, 17.15 and 13.15, respectively. The respective values of Overall Accuracy and the areas under the ROC curve were greater than 0.85 and 0.930, implying that each threshold performed excellently in identifying heat occurrence. Based on the determined critical thresholds, accumulated harmful temperature (Tcum), number of heat days (HD), first heat date (FHD) and last heat date (LHD) were presented to characterize heat exposure. It was clear that Tcum and HD exhibited a north-to-south increasing trend from 1971 to 2020, with the obvious increasing occurrence in most parts of the study region through the period of 2010 to 2020. FHD occurred earlier in most stations except the northeast parts, while LHD ended later in southern MLRYR. Exploring heat critical thresholds at different phenological stages highlighted in this study can help decision-makers monitor and evaluate heat exposure to single-season rice in MLRYR and further develop mitigation strategies to ensure rice production security.