Future Runoff Analysis in the Mekong River Basin under a Climate Change Scenario Using Deep Learning

Abstract

In establishing adequate climate change policies regarding water resource development and management, the most essential step is performing a rainfall-runoff analysis. To this end, although several physical models have been developed and tested in many studies, they require a complex grid-based parameterization that uses climate, topography, land-use, and geology data to simulate spatiotemporal runoff. Furthermore, physical rainfall-runoff models also suffer from uncertainty originating from insufficient data quality and quantity, unreliable parameters, and imperfect model structures. As an alternative, this study proposes a rainfall-runoff analysis system for the Kratie station on the Mekong River mainstream using the long short-term memory (LSTM) model, a data-based black-box method. Future runoff variations were simulated by applying a climate change scenario. To assess the applicability of the LSTM model, its result was compared with a runoff analysis using the Soil and Water Assessment Tool (SWAT) model. The following steps (dataset periods in parentheses) were carried out within the SWAT approach: parameter correction (2000–2005), verification (2006–2007), and prediction (2008–2100), while the LSTM model went through the process of training (1980–2005), verification (2006–2007), and prediction (2008–2100). Globally available data were fed into the algorithms, with the exception of the observed discharge and temperature data, which could not be acquired. The bias-corrected Representative Concentration Pathways (RCPs) 4.5 and 8.5 climate change scenarios were used to predict future runoff. When the reproducibility at the Kratie station for the verification period of the two models (2006–2007) was evaluated, the SWAT model showed a Nash–Sutcliffe efficiency (NSE) value of 0.84, while the LSTM model showed a higher accuracy, NSE = 0.99. The trend analysis result of the runoff prediction for the Kratie station over the 2008–2100 period did not show a statistically significant trend for neither scenario nor model. However, both models found that the annual mean flow rate in the RCP 8.5 scenario showed greater variability than in the RCP 4.5 scenario. These findings confirm that the LSTM runoff prediction presents a higher reproducibility than that of the SWAT model in simulating runoff variation according to time-series changes. Therefore, the LSTM model, which derives relatively accurate results with a small amount of data, is an effective approach to large-scale hydrologic modeling when only runoff time-series are available.

Deep learning shows declining groundwater levels in Germany until 2100 due to climate change

“…Related studies with applications of ANNs either used a very small number of wells 27 – 29 and limited time horizons 27 , 28 or use ANNs without directly presenting future climate signals to the ANN 29 . In the case of streamflow runoff simulation, however, ANNs have been successfully applied to analyze the future development under climate change influences in several catchments all over California 30 as well as in two catchments in China 31 , 32 .…”

Deep learning shows declining groundwater levels in Germany until 2100 due to climate change

“…Related studies with applications of ANNs either used a very small number of wells [23][24][25] and limited time horizons 23,24 or use ANNs without directly presenting future climate signals to the ANN 25 . In case of stream ow runoff simulation, however, ANNs have been successfully applied to analyze the future development under climate change in uences in several catchments all over California 26 as well as two catchments in China 27,28 .…”

Regional Economy Using Hybrid Sequence-to-Sequence-Based Deep Learning Approach

“…Techniques Evaluation [11] AI to reducing the cost in ML Used better with complex data [12] CNN with three levels of distribution Used for highly educated people in IT issue [13] Statistical analysis of CAS thinking &NN algorithm Used for stock market prediction even small data [14] LSTM &SWAT algorithms of growing strategies Better with hydropower domain and speed growing [15] DL techniques of AI Used for updated dataset continuously [16] Pre and postregional earthquake assessment with DL technique Damaged dataset or missing previously part [4] GRU encoder with DNN Online dataset and huge amount of data growth. Resources, labour, and the efficiency of capital and labour inputs and outputs are direct factors; technological development, natural resources, natural environments, and indirect variables are socioeconomic systems and economic policy amount of capital and the productivity of labour inputs.…”