Work

A novel hybrid machine learning approach for δ13C spatial prediction in polish hard-water lakes

Year: 2025

Type: article

Abstract: Comprehension of carbon cycling, climate change, paleoecology, environmental reconstruction, and aquatic ecosystem health is essential for the environmental sciences, and one of the invaluable tools is the δ 13 C record of lake deposits. In this study, we propose a novel hybrid machine learning (ML) algorithm known as the ARAMT model, which combines two key components: a meta-classifier of additive regression (AR) and a base classifier of alternating model trees (AMT). The AR-AMT hybrid model significantly enhances the prediction of carbon isotopes (δ 13 C) by addressing limitations in existing methodologies. For the first time, this model is used to predict the spatial prediction of a stable isotope in Polish lakes. The δ 13 C for 30 Polish lakes is determined using the calcite (CaCO 3 ) precipitated in the near-surface layers of the lakes (epilimnion). The chemical composition (Ca 2+ , HCO 3 − , Na, K, sulfates, fluorides, Cl, Mg, and P) and temperature of the surface water at a depth of 1 m is analyzed seasonally. The current approaches for predicting δ 13 C have demonstrated shortcomings in accuracy and precision. In this study, a random forest (RF), M5P, AMT, and Gaussian process (GP) are the four cutting-edge ML algorithms that are compared with the proposed hybrid model (ARAMT). In accordance with the results, the ARAMT hybrid model performed more effectively in predicting δ 13 C than the other benchmark ML methods ( R 2 = 0.9882, MAE = 0.456, and RMSE = 0.527), the others giving: AMT ( R 2 = 0.982, MAE = 0.558, and RMSE = 0.347), RF ( R 2 = 0.8014, MAE = 0.612, and RMSE = 0.550), M5P ( R 2 = 0.7508, MAE = 0.813, and RMSE = 0.701), and GP ( R 2 = 0.7315, MAE = 0.768, and RMSE = 0.683). Although the AR-AMT hybrid doesn't directly preserve lake ecosystems, the enhanced accuracy of its δ 13 C predictions by providing a more detailed understanding of carbon cycling dynamics can indirectly inform and improve lake ecosystem health and management.

Source: Ecological Informatics

DOI: 10.1016/j.ecoinf.2025.103187

Authors: Himan Shahabi, Ataollah Shirzadi, Alicja Ustrzycka, Natalia Piotrowska, Janusz Filipiak, Marzieh Hajizadeh Tahan

Institutions: Silesian University of Technology, University of Kurdistan, University of Gdańsk

Language: English

Topic: Isotope Analysis in Ecology

Subfield: Ecology

Field: Environmental Science

Domain: Physical Sciences

SDGs: Climate action, Clean water and sanitation

Open Access status: gold

Estimated APC paid: $2,770