Combining spatial autocorrelation with artificial intelligence models to estimate spatial distribution and risks of heavy metal pollution in agricultural soils

• Published in: Environmental monitoring and assessment 2023-02, Vol.195 (2), p.317-317, Article 317
• Main Authors: Günal, Elif, Budak, Mesut, Kılıç, Miraç, Cemek, Bilal, Sırrı, Mesut
• Format: Article
• Language: English
• Subjects: Adaptive systems; Agricultural land; Agricultural pollution; Algorithms; Artificial Intelligence; Artificial neural networks; Atmospheric Protection/Air Quality Control/Air Pollution; Autocorrelation; Cadmium; Cadmium - analysis; CD20 antigen; China; Contamination; Deep learning; Depth; Distribution; Distribution patterns; Earth and Environmental Science; Ecology; Ecotoxicology; Electrical conductivity; Electrical resistivity; Emissions; Environment; Environmental Management; Environmental monitoring; Environmental Monitoring - methods; Environmental risk; Environmental science; Factor analysis; Food contamination; Food safety; Fuzzy logic; Heavy metals; Heterogeneity; Humans; Lead; Lead - analysis; Machine learning; Metal concentrations; Metal content; Metals, Heavy - analysis; Modelling; Monitoring/Environmental Analysis; Neural networks; Nickel; Nickel - analysis; Organic matter; Pollutants; Pollution; Pollution index; Risk Assessment; Risk levels; Root-mean-square errors; Soil; Soil - chemistry; Soil contamination; Soil depth; Soil lime; Soil Pollutants - analysis; Soil pollution; Soil surfaces; Spatial Analysis; Spatial data; Spatial discrimination learning; Spatial distribution
• ISSN: 0167-6369; 1573-2959
• DOI: 10.1007/s10661-022-10813-2

Information on spatial distribution and potential sources of heavy metals in agricultural lands is very important for human health and food safety. In this study, pollution degree of lead (Pb), cadmium (Cd), and nickel (Ni) in Yüksekova Plain, located on the border in the southeastern part of Turkey, was evaluated by geoaccumulation index (Igeo), modified contamination factor (mCdeg), and Nemerow pollution index (PI Nemerow ) combined with spatial autocorrelation using deep learning algorithms. A total of 304 soil samples were collected from two different depths (0–20 and 20–40 cm) in the study area, which covered 17.5 thousand ha land. Covariates were determined for spatial distribution models of Pb, Cd, and Ni by factor analysis (FA). Spatial distribution models for surface soils were developed using pedovariables (silt, sand, clay lime, organic matter, electrical conductivity, pH, Ca, and Na) determined by the FA and Igeo and mCdeg values by artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) models. The estimation success of models for different depths was assessed by root mean square error (RMSE), mean absolute percent error (MAPE), and Taylor diagrams. The RMSE and MAPE values showed a strong correlation between heavy metal contents and the covariates. The RMSE values of ANN-Ni 0-20 , ANN-Ni 20-40 , ANN-Pb 0-20 , ANN-Cd 0-20 , and ANN-Cd 20-40 models (0.01240, 0.07257, 0.0039, 0.00045, 0.00044, and 0.04607, respectively) confirmed the success of the models. Likewise, the MAPE values between 0.2 and 8.5% indicated that all models were very good predictors. In addition, the Taylor diagrams showed that the estimation performance of ANFIS and ANN models are compatible. The Igeo Ni and Igeo Pb values in both models at both depths indicated that strongly to extremely polluted (4–5) areas are quite high in the study area, while the Igeo Cd values revealed that unpolluted areas are widespread. The mC deg index value showed a moderate to high contamination at the first depth, while very high contamination at the second depth in most of the study area. Spatial distribution of PI Nemerow revealed that moderate pollution (2–3) is common in both soil depths of the study area. The PI Nemerow of subsurface layer was between 0.91 and 1 (warning limit class) in a small part of the study area. The results showed that vertical mobility of heavy metals is closely related to pedovariables. In addition, the ANN and ANFIS models are capable of