Accuracy, uncertainty, and interpretability assessments of ANFIS models to predict dust concentration in semi-arid regio
- PDF / 2,156,997 Bytes
- 15 Pages / 595.276 x 790.866 pts Page_size
- 8 Downloads / 167 Views
RESEARCH ARTICLE
Accuracy, uncertainty, and interpretability assessments of ANFIS models to predict dust concentration in semi-arid regions Zohre Ebrahimi-Khusfi 1
&
Ruhollah Taghizadeh-Mehrjardi 2,3 & Ali Reza Nafarzadegan 4
Received: 3 August 2020 / Accepted: 20 September 2020 # Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract Accurate prediction of the dust concentration (DC) is necessary to reduce its undesirable environmental effects in different geographical areas. Although the adaptive neuro-fuzzy inference system (ANFIS) is a powerful model for predicting dust events, no attempt has been made to investigate its uncertainty and interpretability. In this study, therefore, the uncertainty of the ANFIS model was quantified using uncertainty estimation based on local errors and clustering methods. Furthermore, we used a modelagnostic interpretation to make the ANFIS model interpretable. In addition, we used the bat optimization algorithm (BAT) to increase the prediction accuracy of the ANFIS model. Seven explanatory variables were chosen for predicting DC in the cold and warm months across semi-arid regions of Iran. The results showed that the ANFIS+BAT model increased the correlation coefficient by 10% and 16% for predicting DC in the cold and warm months, respectively, compared with the ANFIS model. Furthermore, the uncertainty analysis indicated a lower prediction interval (i.e., lower uncertainty) for the ANFIS+BAT model compared with the ANFIS model for predicting DC in the cold and warm months. In addition, the model-agnostic interpretation tool findings indicated the highest contributions of air temperature and maximum wind speed for predicting DC in the cold and warm months, respectively. Prediction of DC using the proposed model will allow decision-makers to better plan for measures to mitigate the risks of wind erosion and air pollution. Keywords Air pollution . ANFIS . Bat optimization algorithm . Interpretability . Machine learning . Uncertainty
Introduction Zohre Ebrahimi-Khusfi and Ruhollah Taghizadeh-Mehrjardi contributed equally. Responsible editor: Marcus Schulz * Zohre Ebrahimi-Khusfi [email protected] * Ruhollah Taghizadeh-Mehrjardi [email protected]; [email protected] Ali Reza Nafarzadegan [email protected] 1
Department of Natural Science, Faculty of Natural Resources, University of Jiroft, Jiroft, Iran
2
Department of Geosciences, Soil Science and Geomorphology, University of Tübingen, Tubingen, Germany
3
Faculty of Agriculture and Natural Resources, Ardakan University, Ardakan, Iran
4
Department of Natural Resources Engineering, University of Hormozgan, Bandar-Abbas, Hormozgan, Iran
Wind erosion is one of the major threats to soils in the windsensitive areas, with an undesirable impact on soil organic carbon (Chappell et al. 2019), air quality (Ashrafi et al. 2017), economic activities (Barbulescu and Nazzal 2020), agricultural products (Taheri et al. 2020), human health (Oduber et al. 201
Data Loading...
