TY - JOUR
T1 - Predicting increments in heavy metal contamination in farmland soil
AU - Chen, Jieh Haur
AU - Yeh, Meng Fen
AU - Wang, Jui Pin
AU - Wei, Hsi Hsien
N1 - Publisher Copyright:
© The Author(s), under exclusive licence to Springer Nature B.V. 2024.
PY - 2024
Y1 - 2024
N2 - Traditional pollution risk assessment approaches face difficulty to effectively reflect the current state of pollution. The study is to predict increments in heavy metal contamination in farmland soil using logistic regression and neural networks in Taoyuan City, following the remediation of agricultural land pollution. The study has sampled all contaminated 2,824 parcels of farmland in Taoyuan City, involving 9,674 data entries in recent 20 years. The increment of copper, zinc, and cadmium was predicted with an accuracy of 82%, 83%, and 91%, respectively, using logistic regression and ensemble learning. In particular, the predictive power of cadmium is the best, while the neural network model demonstrated a good fit between the predicted copper, zinc, and cadmium increments and the actual values. The R2 values obtained were 0.81, 0.82, and 0.98 respectively, with the predictive power of cadmium being particularly significant. The model can effectively predict the increments in heavy metals such as copper, zinc, and cadmium in the farmland and select the farmland with the highest pollution recurrence risk as the main target for soil surveys.
AB - Traditional pollution risk assessment approaches face difficulty to effectively reflect the current state of pollution. The study is to predict increments in heavy metal contamination in farmland soil using logistic regression and neural networks in Taoyuan City, following the remediation of agricultural land pollution. The study has sampled all contaminated 2,824 parcels of farmland in Taoyuan City, involving 9,674 data entries in recent 20 years. The increment of copper, zinc, and cadmium was predicted with an accuracy of 82%, 83%, and 91%, respectively, using logistic regression and ensemble learning. In particular, the predictive power of cadmium is the best, while the neural network model demonstrated a good fit between the predicted copper, zinc, and cadmium increments and the actual values. The R2 values obtained were 0.81, 0.82, and 0.98 respectively, with the predictive power of cadmium being particularly significant. The model can effectively predict the increments in heavy metals such as copper, zinc, and cadmium in the farmland and select the farmland with the highest pollution recurrence risk as the main target for soil surveys.
KW - Farmland pollution
KW - Heavy metal contamination
KW - Neural networks
KW - Prediction
UR - http://www.scopus.com/inward/record.url?scp=85207021959&partnerID=8YFLogxK
U2 - 10.1007/s10668-024-05443-2
DO - 10.1007/s10668-024-05443-2
M3 - 期刊論文
AN - SCOPUS:85207021959
SN - 1387-585X
JO - Environment, Development and Sustainability
JF - Environment, Development and Sustainability
ER -