What question did this study set out to answer?

This study aims to develop a robust framework for forecasting water levels in Qinghai Lake, which has experienced significant hydrological changes.

June 14, 2026Open Access

A Hybrid ARIMA-CNN-LSTM Framework Based on Serial Decomposition for Non-Stationary Water Level Forecasting in Qinghai Lake

Key Points

This study aims to develop a robust framework for forecasting water levels in Qinghai Lake, which has experienced significant hydrological changes.
Developed a GeoAI framework utilizing ARIMA and CNN-LSTM for water level forecasting.
Used annual water level observations from 1960 to 2025, training from 1960 to 2012 and validating from 2013 to 2025.
Measured performance using RMSE, MAE, and MSE metrics for predictive accuracy.
Achieved RMSE of 0.2033 m, MAE of 0.1727 m, and MSE of 0.0413 m2 indicating superior performance over benchmark models.
Forecasting suggests water levels will rise to approximately 3204.08 m by 2056, although growth rate may slow.
Demonstrated improved accuracy by separating deterministic signals from nonlinear variability.

Abstract

Qinghai Lake, the largest endorheic saline lake in China, has undergone a pronounced hydrological regime shift from a multi-decadal decline to a rapid post-2004 recovery, reflecting strong hydroclimatic non-stationarity in the northeastern Tibetan Plateau (TP). This paper supplements the current water level and lake area status of Qinghai Lake to provide basic background for future prediction. Reliable forecasting of such climate sensitive lake systems remains difficult because conventional statistical models often fail to capture non-linear fluctuations, whereas standalone deep learning models may overlook long-term deterministic evolution. To address this challenge, we developed a serial decomposition GeoAI framework that integrates autoregressive integrated moving average (ARIMA), one-dimensional convolutional neural networks (1D-CNNs), and long short-term memory (LSTM) networks for non-stationary water level forecasting. Using annual water level observations from 1960 to 2025, the ARIMA component was first used to extract the low-frequency deterministic trend, after which the CNN-LSTM module reconstructed the nonlinear residual variability. The model was trained on the 1960–2012 period and validated over 2013–2025, which represents the most dynamic expansion stage of Qinghai Lake. The hybrid framework outperformed the benchmark models, achieving a Root Mean Square Error (RMSE) of 0.2033 m, Mean Absolute Error (MAE) of 0.1727 m, and Mean Squared Error (MSE) of 0.0413 m2 during validation. The decomposition strategy effectively reduced phase lag and amplitude attenuation, improving both predictive accuracy and process interpretability. Multi-step forecasting for 2026–2056 suggests that Qinghai Lake will continue to rise, reaching approximately 3204.08 m by 2056, although the growth rate is projected to slow as negative hydrological feedback strengthen. By explicitly separating deterministic climate scale signals from nonlinear short-term variability, the proposed framework provides a robust and transferable geoinformation based tool for forecasting water level dynamics and supporting adaptive management in climate sensitive, data scarce lake basins.

Read Full Paperexternally

Mark Helpful

Bookmark

Relay

View Full Paper