| 1. |
- Long, Junshui, et al.
(författare)
-
Hydrological Projections in the Third Pole Using Artificial Intelligence and an Observation-Constrained Cryosphere-Hydrology Model
- 2024
-
Ingår i: EARTHS FUTURE. - 2328-4277. ; 12:4
-
Tidskriftsartikel (refereegranskat)abstract
- The water resources of the Third Pole (TP), highly sensitive to climate change and glacier melting, significantly impact the water and food security of millions in Asia. However, projecting future spatial-temporal runoff changes for TP's mountainous basins remains a formidable challenge. Here, we've leveraged the long short-term memory model (LSTM) to craft a grid-scale artificial intelligence (AI) model named LSTM-grid. This model has enabled the production of hydrological projections for the seven major river basins of TP. The LSTM-grid model integrates monthly precipitation, air temperature, and total glacier mass changes (total_GMC) data at a 0.25-degree model grid. Training the LSTM-grid model employed gridded historical monthly runoff and evapotranspiration data sets generated by an observation-constrained cryosphere-hydrology model at the headwaters of seven TP river basins during 2000-2017. Our results demonstrate the LSTM grid's effectiveness and usefulness, exhibiting a Nash-Sutcliffe Efficiency coefficient exceeding 0.92 during the verification periods (2013-2017). Moreover, river basins in the monsoon region exhibited a higher rate of runoff increase compared to those in the westerlies region. Intra-annual projections indicated notable increases in spring runoff, especially in basins where glacier meltwater significantly contributes to runoff. Additionally, the LSTM-grid model aptly captures the runoff changes before and after the turning points of glacier melting, highlighting the growing influence of precipitation on runoff after reaching the maximum total_GMC. Therefore, the LSTM-grid model offers a fresh perspective for understanding the spatiotemporal distribution of water resources in high-mountain glacial regions by tapping into AI's potential to drive scientific discovery and provide reliable data. Water resources of the Third Pole (TP) significantly impact the water and food security in Asia. However, projecting future spatial-temporal runoff changes for the TP's mountain basins remains a challenge. Here, we've leveraged the long short-term memory (LSTM) model to craft a gridded artificial intelligence model (named LSTM-grid). Trained by the outputs of an observation-constrained distributed cryosphere-hydrology model, the LSTM-grid has enabled reliable spatiotemporal runoff and evapotranspiration projections for the headwaters of seven TP rivers (Yellow, Yangtze, Mekong, Salween, Brahmaputra, Ganges, Indus) till 2100. Our projections show that the river basins in the monsoon region exhibit a higher rate of runoff increase compared to those in the westerlies region. In particular, the proposed approach in this study can reasonably capture the runoff changes before and after the turning points of glacier melting without prior knowledge, highlighting the growing influence of precipitation on runoff after reaching the maximum total glacier mass changes (of a river basin). Hence, the LSTM-grid model provides a fresh perspective for understanding the spatiotemporal distribution of water resources in high-mountain glacial regions. We use artificial intelligence and an observation-constrained cryosphere-hydrology model to project future runoff for seven high-mountain Third Pole basins Results show that river basins in the monsoon region exhibited a higher rate of runoff increase compared to those in the westerlies region The proposed approach can aptly simulate runoff changes before and after the turning points of glacier melting without prior knowledge
|
|
| 2. |
- Liu, Ruishun, et al.
(författare)
-
Cryosphere-Hydrometeorology Observations for a Water Tower Unit on the Tibetan Plateau Using the BeiDou-3 Navigation Satellite System
- 2024
-
Ingår i: BULLETIN OF THE AMERICAN METEOROLOGICAL SOCIETY. - 0003-0007 .- 1520-0477. ; 105:3
-
Tidskriftsartikel (refereegranskat)abstract
- Life and civilization in arid regions depend on the availability of freshwater. Arid alpine river basins, where hydrological processes are highly sensitive to rapid warming, act as vital water towers for lowland oases. However, scientific understanding of precipitation variability and related cryosphere-hydrology processes is extremely limited because of the scarcity of in situ observations. The upper Danghe River basin (UDB; similar to 14,000 km2) is an arid and westerly dominated basin on the northeastern Tibetan Plateau and is the water source for the Dunhuang Oasis in China. We have established a comprehensive cryosphere-hydrometeorology observation network in the basin since 2014. At present, the network consists of 21 automatic rain gauges, 22 soil freeze-thaw monitoring stations, 4 automatic weather stations (AWS), and a 50-m gradient meteorological tower with an eddy covariance system. In particular, the 18 sites, located in remote areas without public networks, are equipped with new -generation BeiDou-3 communication terminals that enable the observations to be easily, safely, and reliably read and quality controlled in near-real time from offices in the city or at home. This integrated observation network over the UDB that facilitates the monitoring of cryosphere-hydrology processes, land-atmosphere interactions, and local weather processes. In addition, the observations are helpful for the objective evaluation, and continual improvement, of hydrological models, satellite -retrieval products, and reanalysis datasets. Finally, the network is expected to promote a better understanding of the status and role of water towers in arid zones and to provide basic data support for the sustainable development of the Dunhuang Oasis and the Belt and Road.
|
|
| 3. |
- Xu, Jie, et al.
(författare)
-
Totaling river discharge of the third pole from satellite imagery
- 2024
-
Ingår i: REMOTE SENSING OF ENVIRONMENT. - 0034-4257 .- 1879-0704. ; 308
-
Tidskriftsartikel (refereegranskat)abstract
- The high-mountain Third Pole (TP) in Asia is undergoing rapid warming, profoundly impacting river discharge. Changes in precipitation and the degradation of glaciers and permafrost exert a substantial impact on TP rivers, affecting millions downstream. Nevertheless, conventional estimation methods that rely on in -situ observations and models face considerable challenges due to inconsistent data quality and availability, complex terrain, and difficulty in representing hydrological processes. Here, we harnessed the power of high-resolution (3 m) Dove/ PlanetScope satellite images to meticulously measure river width and propose a novel formula for estimating discharge. This approach facilitates a coherent assessment of discharge at various river section shapes. Its efficacy is demonstrated through applying to thirteen high-mountain TP rivers, revealing an estimated total mountain discharge of 3786 billion m 3 during 2017 - 2021, equaling water from approximately 167 Great Lakes. These findings have immediate implications for integrated water resources management at the poorly-gauged transboundary basins of Asia.
|
|
