Search

Drought is one of the key limiting factors for potato yield in the northern single cropping area (NSCA) in China. To analyze the impact of drought on potato yield in the NSCA, this study first analyzed the variation of dry/wet conditions in the plantable areas on a seasonal scale using the standardized precipitation evapotranspiration index (SPEI). Secondly, the changes in yield structure in the last 36 years were systematically analyzed and divided the total yield change into planting area contribution and climate yield contribution. Finally, a regression model of the seasonal drought index and contributing factors of total yield change in different administrative regions was constructed. The results showed that the main factors affecting the total potato yield of the NSCA began to change from yield to planting area in the 1990s, while the barycenter of the output structure and population moved to the southwest, with grassland being the main source; dry/wet conditions (year i) had varying degrees of effect on contributing factors (year i, year i + 1) of total yield change in different administrative regions that were not limited to the growing season; the non-overlap of high-yield area, high-adaptability area and planting area was the urgent problem to be solved for the NSCA. The results of this study can provide a scientific basis for NSCA crop management and communication with farmers, providing new ideas for sustainable production in other agricultural regions in the world. [ABSTRACT FROM AUTHOR]

Under the background of global warming, the frequent occurrence and long-term persistence of drought events have substantial negative effects on agricultural production. As the main maize production area in midwestern Jilin Province, frequent drought and a shortage of irrigation water pose substantial threats to the production of maize. We analyzed the balance of water supply and demand in each growth period and the degree of maize yield affected by drought. The results indicate that the FIO-ESM climate model can effectively simulate the changes in temperature and precipitation, and was highly applicable to the study area. From 1980 to 2020, the drought risk indices for the sowing to jointing, jointing to tasseling, tasseling to milk-ripe, and milk-ripe to maturity stages were 0.62, 0.52, 0.48, and 0.60, respectively. In the future, the chances of a RCP8.5 scenario drought risk and an enhanced RCP4.5 scenario have eased. Spatially, the high-risk areas shift in a "west−central−southwest" pattern. Effective precipitation will decrease in the future, while the increasing water requirement of maize increases the dependence on irrigation water. The irrigation requirement index is more than 70% for all periods, particularly in the milk-ripe to maturity stage. The relative meteorological yields were positively correlated with the CWDI of the whole growth period, with the rate of reduction in maize yield and the yield reduction coefficient of variation at a high level of risk between 1980 and 2020. In the future, the negative impact of drought risk on the yield of maize lessened with no obvious trend in production. In particular, the rate of reduction and reduction coefficient of variation for the RCP8.5 scenario were 1.24 and 1.09, respectively. [ABSTRACT FROM AUTHOR]

Among the most frequent and dangerous natural hazards, landslides often result in huge casualties and economic losses. Landslide susceptibility mapping (LSM) is an excellent approach for protecting and reducing the risks by landslides. This study aims to explore the performance of Bayesian optimization (BO) in the random forest (RF) and gradient boosting decision tree (GBDT) model for LSM and applied in Shuicheng County, China. Multiple data sources are used to obtain 17 conditioning factors of landslides, Borderline-SMOTE and Randomundersample methods are combined to solve the imbalanced sample problem. RF and GBDT models before and after BO are adopted to calculate the susceptibility value of landslides and produce LSMs and these models were compared and evaluated using multiple validation approach. The results demonstrated that the models we proposed all have high enough model accuracy to be applied to produce LSM, the performance of the RF is better than the GBDT model without BO, while after adopting the Bayesian optimized hyperparameters, the prediction accuracy of the RF and GBDT models is improved by 1% and 7%, respectively and the Bayesian optimized GBDT model is the best for LSM in this four models. In summary, the Bayesian optimized RF and GBDT models, especially the GBDT model we proposed for landslide susceptibility assessment and LSM construction has a very good application performance and development prospects. [ABSTRACT FROM AUTHOR]

Landslides are among the most frequent natural hazards in the world. Rainfall is an important triggering factor for landslides and is responsible for topples, slides, and debris flows—three of the most important types of landslides. However, several previous relevant research studies covered general landslides and neglected the rainfall–topples–slides–debris flows disaster chain. Since landslide hazard mapping (LHM) is a critical tool for disaster prevention and mitigation, this study aimed to build a GeoDetector and Bayesian network (BN) model framework for LHM in Shuicheng County, China, to address these geohazards. The GeoDetector model will be used to screen factors, eliminate redundant information, and discuss the interaction between elements, while the BN model will be used for constructing a causality disaster chain network to determine the probability and risk level of the three types of landslides. The practicability of the BN model was confirmed by error rate and scoring rules validation. The prediction accuracy results were tested using overall accuracy, Matthews correlation coefficient, relative operating characteristics curve, and seed cell area index. The proposed framework is demonstrated to be sufficiently accurate to construct the complex LHM. In summary, the combination of the GeoDetector and BN model is very promising for spatial prediction of landslides. [ABSTRACT FROM AUTHOR]