Table 1 Critical analysis of contemporary state-of-the-art studies
From: Shapley-based interpretation of deep learning models for wildfire spread rate prediction
Sr No. | Approach | Objective | Model | Used explainable AI? |
|---|---|---|---|---|
1 | (Cheney et al. 1998) | The prediction of the spread of flames in grasslands | Empirical models | × |
2 | (Arashpour et al. 2022) | Predicting environmental phenomena | Neural Networks | × |
3 | (Wadhwani et al. 2021) | Predicting environmental phenomena | Neural Networks | × |
4 | (Pesantez et al. 2020) | Predicting environmental phenomena | SVR | × |
5 | (Cui et al. 2021) | Predicting environmental phenomena | GPR | × |
6 | (Jaxa-Rozen and Kwakkel 2018) | Predicting environmental phenomena | Regression Tree | × |
7 | (Pais et al. 2021) | The present study focuses on the utilization of machine learning (ML) algorithms to forecast and simulate the spread of fire | ML model | × |
8 | (Hodges and Lattimer 2019) | The objective is to replicate wildfire simulations | Deep convolutional inverse graphics network | × |
10 | Proposed Study | Optimization of ML Techniques for Wildfire Spread Comparative Assessment for Predictive Precision Interpretation and Impact Analysis Using XAI | Transformer encoder SVM: SVR, QSV, GSV ANN: NNN, BNN, WNN | ✓ |