The Science of The Total Environment, Год журнала: 2024, Номер 953, С. 176099 - 176099
Опубликована: Сен. 10, 2024
Язык: Английский
The Science of The Total Environment, Год журнала: 2024, Номер 953, С. 176099 - 176099
Опубликована: Сен. 10, 2024
Язык: Английский
Journal of Environmental Management, Год журнала: 2025, Номер 375, С. 124410 - 124410
Опубликована: Фев. 1, 2025
Язык: Английский
Процитировано
3Agricultural Water Management, Год журнала: 2024, Номер 295, С. 108772 - 108772
Опубликована: Март 13, 2024
Sub-seasonal drought forecasting is crucial for early warning in estimating agricultural production and optimizing irrigation management, as skills are relatively weak during this period. Soil moisture exhibits stronger persistence compared to other climate system quantities, which makes it especially influential shaping land-atmosphere feedback, thus supplying a unique insight into forecasting. Relying on the soil memory, study investigates combination of multiple deep-learning modules sub-seasonal indices hindcast Huai River basin China, using long-term ERA5-Land records with noise-assisted data analysis tool. The inter-compared models include hybrid model committee machine framework. results show that performance framework can be improved help series decomposition skill not impaired lead time increases. Overall, highlights potential combining memory improve
Язык: Английский
Процитировано
7Global Change Biology, Год журнала: 2025, Номер 31(3)
Опубликована: Март 1, 2025
ABSTRACT Future variations of global vegetation are paramount importance for the socio‐ecological systems. However, up to now, it is still difficult develop an approach project considering spatial heterogeneities from vegetation, climate factors, and models. Therefore, this study first proposes a novel model framework named GGMAOC (grid‐by‐grid; multi‐algorithms; optimal combination) construct using six algorithms (i.e., LR: linear regression; SVR: support vector RF: random forest; CNN: convolutional neural network; LSTM: long short‐term memory; transformer) based on five climatic factors Tmp: temperature; Pre: precipitation; ET: evapotranspiration, SM: soil moisture, CO 2 ). The employed future changes in leaf area index (LAI) four sub‐regions: high‐latitude northern hemisphere (NH), mid‐latitude NH, tropics, southern hemisphere. Our results indicate that LAI will continue increase, with greening rate expanding 2.25 times NH by 2100 against 1982–2014 period. Moreover, RF shows strong applicability In study, we introduce innovative GGMAOC, which provides new scheme environmental geoscientific research.
Язык: Английский
Процитировано
1The Science of The Total Environment, Год журнала: 2024, Номер 932, С. 172865 - 172865
Опубликована: Апрель 29, 2024
Язык: Английский
Процитировано
3Environmental Research, Год журнала: 2025, Номер unknown, С. 120919 - 120919
Опубликована: Янв. 1, 2025
Язык: Английский
Процитировано
0The Science of The Total Environment, Год журнала: 2025, Номер 965, С. 178672 - 178672
Опубликована: Фев. 1, 2025
Язык: Английский
Процитировано
0Agricultural Water Management, Год журнала: 2025, Номер 312, С. 109415 - 109415
Опубликована: Март 6, 2025
Язык: Английский
Процитировано
0Remote Sensing, Год журнала: 2024, Номер 16(19), С. 3581 - 3581
Опубликована: Сен. 26, 2024
The cycle of carbon and water in ecosystems is likely to be significantly impacted by future climate change, especially semiarid regions. While a considerable number investigations have scrutinized the repercussions impending climatic transformations on either or cycles, there scarcity studies delving into effects change coupled water–carbon process its interrelationships. Based this, Sanchuan River Basin, an ecologically fragile region Loess Plateau, was chosen as research area. General circulation model-projected scenarios (SSP1-2.6, SSP2-4.5, SSP5-8.5) ecohydrological model were integrated predict (2021–2100) changes actual evapotranspiration (ET), surface runoff (Rs), net primary productivity (NPP), soil organic (SOC). results indicated that under impacts warming humidification, ET, Rs, NPP will increase 0.17–6.88%, 1.08–42.04%, 2.18–10.14%, respectively, while SOC decrease 3.38–10.39% basin. A path analysis showed precipitation temperature had significant ET NPP, Rs more sensitive precipitation, impact SOC. Furthermore, all average ET-NPP correlation coefficient greater than 0.6, showing basin’s tightly coupled. However, SSP5-8.5, Rs-NPP decreased from −0.35 near-future period −0.44 far-future period, which may indicate positive effect increased would barely offset negative large increases. As foundation for achieving sustainable resource management ecosystem preservation policies, this study can utilized build adaptation methods manage change.
Язык: Английский
Процитировано
1The Science of The Total Environment, Год журнала: 2024, Номер 953, С. 176099 - 176099
Опубликована: Сен. 10, 2024
Язык: Английский
Процитировано
0