Machine Learning Reveals a Significant Shift in Water Regime Types Due to Projected Climate Change

Abstract

A water regime type is a cumulative representation of seasonal runoff variability in a textual, qualitative, or quantitative form developed for a particular period. The assessment of the respective water regime type changes is of high importance for local communities and water management authorities, increasing their awareness and opening strategies for adaptation. In the presented study, we trained a machine learning model—the Random Forest classifier—to predict water regime types in northwest Russia based on monthly climatological hydrographs derived for a historical period (1979–1991). Evaluation results show the high efficiency of the trained model with an accuracy of 91.6%. Then, the Random Forest model was used to predict water regime types based on runoff projections for the end of the 21st century (2087–2099) forced by four different General Circulation Models (GCM) and three Representative Concentration Pathway scenarios (RCP). Results indicate that climate is expected to modify water regime types remarkably. There are two primary directions of projected changes. First, we detect the tendency towards less stable summer and winter flows. The second direction is towards a shift in spring flood characteristics. While spring flooding is expected to remain the dominant phase of the water regime, the flood peak is expected to shift towards earlier occurrence and lower magnitude. We identified that the projected changes in water regime types are more pronounced in more aggressive RCP scenarios.

Identifying Climate Change Impacts On Hydrological Behavior On Large-Scale With Machine Learning Algorithms

“…The basis of the metrics for assessing the quality of classification is the contingency matrix (Townsend 1971). The most common metric is accuracy, which was also used as a metric in the work (Ayzel 2021). This metric was used to evaluate the classification result, despite the fact that it has a significant drawback.…”

“…The main characteristics of the hydrological regime of rivers are the character of inflow components, morphodynamic and climatic conditions (Blöschl et al 2017;Hall and Blöschl 2018;Frolova et al 2021;Frolova et al 2020;. The local unevenness of these values has led to the development of various methods for zoning rivers according to the types of water regime (Water regime… 2001;Ayzel 2021). The study of geographic dependencies in the formation of the water regime, the analysis of the impact of economic activity -all of this is necessary to improve the existing methods of hydrological calculations.…”

“…with a model without them demonstrated that it is possible to achieve comparable model quality without static characteristics of a watershed It's rare to find a study with the use of machine learning methods in the problems of classifying the water regime for Russian rivers. In fact, the study (Ayzel 2021) is a unique work. A map of water regime types in the USSR is used as a class reference (Water regime... 2001).…”