Attribution of Runoff Variation in Reservoir Construction Area: Based on a Merged Deep Learning Model and the Budyko Framework
This study presents a framework to attribute river runoff variations to the combined effects of reservoir operations, land surface changes, and climate variability. We delineated the data into natural and impacted periods. For the natural period, an integrated Long Short-Term Memory and Random Fores...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-01-01
|
| Series: | Atmosphere |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4433/15/2/164 |
| _version_ | 1797298995532398592 |
|---|---|
| author | Lilan Zhang Xiaohong Chen Bensheng Huang Liangxiong Chen Jie Liu |
| author_facet | Lilan Zhang Xiaohong Chen Bensheng Huang Liangxiong Chen Jie Liu |
| author_sort | Lilan Zhang |
| collection | DOAJ |
| description | This study presents a framework to attribute river runoff variations to the combined effects of reservoir operations, land surface changes, and climate variability. We delineated the data into natural and impacted periods. For the natural period, an integrated Long Short-Term Memory and Random Forest model was developed to accurately simulate both mean and extreme runoff values, outperforming existing models. This model was then used to estimate runoff unaffected by human activities in the impacted period. Our findings indicate stable annual and wet season mean runoff, with a decrease in wet season maximums and an increase in dry season means, while extreme values remained largely unchanged. A Budyko framework incorporating reconstructed runoff revealed that rainfall and land surface changes are the predominant factors influencing runoff variations in wet and dry seasons, respectively, and land surface impacts become more pronounced during the impacted period for both seasons. Human activities dominate dry season runoff variation (93.9%), with climate change at 6.1%, while in the wet season, the split is 64.5% to 35.5%. Climate change and human activities have spontaneously led to reduced runoff during the wet season and increased runoff during the dry season. Only reservoir regulation is found to be linked to human-induced runoff changes, while the effects of land surface changes remain ambiguous. These insights underscore the growing influence of anthropogenic factors on hydrological extremes and quantify the role of reservoirs within the impacts of human activities on runoff. |
| first_indexed | 2024-03-07T22:43:08Z |
| format | Article |
| id | doaj.art-f1d75fccb60c4231ae6c3cdab05405c4 |
| institution | Directory Open Access Journal |
| issn | 2073-4433 |
| language | English |
| last_indexed | 2024-03-07T22:43:08Z |
| publishDate | 2024-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Atmosphere |
| spelling | doaj.art-f1d75fccb60c4231ae6c3cdab05405c42024-02-23T15:07:02ZengMDPI AGAtmosphere2073-44332024-01-0115216410.3390/atmos15020164Attribution of Runoff Variation in Reservoir Construction Area: Based on a Merged Deep Learning Model and the Budyko FrameworkLilan Zhang0Xiaohong Chen1Bensheng Huang2Liangxiong Chen3Jie Liu4Guangdong Research Institute of Water Resources and Hydropower, Guangzhou 510620, ChinaSchool of Civil Engineering, Sun Yat-sen University, Guangzhou 510275, ChinaGuangdong Research Institute of Water Resources and Hydropower, Guangzhou 510620, ChinaGuangdong Research Institute of Water Resources and Hydropower, Guangzhou 510620, ChinaGuangdong Research Institute of Water Resources and Hydropower, Guangzhou 510620, ChinaThis study presents a framework to attribute river runoff variations to the combined effects of reservoir operations, land surface changes, and climate variability. We delineated the data into natural and impacted periods. For the natural period, an integrated Long Short-Term Memory and Random Forest model was developed to accurately simulate both mean and extreme runoff values, outperforming existing models. This model was then used to estimate runoff unaffected by human activities in the impacted period. Our findings indicate stable annual and wet season mean runoff, with a decrease in wet season maximums and an increase in dry season means, while extreme values remained largely unchanged. A Budyko framework incorporating reconstructed runoff revealed that rainfall and land surface changes are the predominant factors influencing runoff variations in wet and dry seasons, respectively, and land surface impacts become more pronounced during the impacted period for both seasons. Human activities dominate dry season runoff variation (93.9%), with climate change at 6.1%, while in the wet season, the split is 64.5% to 35.5%. Climate change and human activities have spontaneously led to reduced runoff during the wet season and increased runoff during the dry season. Only reservoir regulation is found to be linked to human-induced runoff changes, while the effects of land surface changes remain ambiguous. These insights underscore the growing influence of anthropogenic factors on hydrological extremes and quantify the role of reservoirs within the impacts of human activities on runoff.https://www.mdpi.com/2073-4433/15/2/164climate changeBudyko frameworkLSTMreservoir operationrunoff variation attribution |
| spellingShingle | Lilan Zhang Xiaohong Chen Bensheng Huang Liangxiong Chen Jie Liu Attribution of Runoff Variation in Reservoir Construction Area: Based on a Merged Deep Learning Model and the Budyko Framework Atmosphere climate change Budyko framework LSTM reservoir operation runoff variation attribution |
| title | Attribution of Runoff Variation in Reservoir Construction Area: Based on a Merged Deep Learning Model and the Budyko Framework |
| title_full | Attribution of Runoff Variation in Reservoir Construction Area: Based on a Merged Deep Learning Model and the Budyko Framework |
| title_fullStr | Attribution of Runoff Variation in Reservoir Construction Area: Based on a Merged Deep Learning Model and the Budyko Framework |
| title_full_unstemmed | Attribution of Runoff Variation in Reservoir Construction Area: Based on a Merged Deep Learning Model and the Budyko Framework |
| title_short | Attribution of Runoff Variation in Reservoir Construction Area: Based on a Merged Deep Learning Model and the Budyko Framework |
| title_sort | attribution of runoff variation in reservoir construction area based on a merged deep learning model and the budyko framework |
| topic | climate change Budyko framework LSTM reservoir operation runoff variation attribution |
| url | https://www.mdpi.com/2073-4433/15/2/164 |
| work_keys_str_mv | AT lilanzhang attributionofrunoffvariationinreservoirconstructionareabasedonamergeddeeplearningmodelandthebudykoframework AT xiaohongchen attributionofrunoffvariationinreservoirconstructionareabasedonamergeddeeplearningmodelandthebudykoframework AT benshenghuang attributionofrunoffvariationinreservoirconstructionareabasedonamergeddeeplearningmodelandthebudykoframework AT liangxiongchen attributionofrunoffvariationinreservoirconstructionareabasedonamergeddeeplearningmodelandthebudykoframework AT jieliu attributionofrunoffvariationinreservoirconstructionareabasedonamergeddeeplearningmodelandthebudykoframework |