Table 1 Critical analysis of contemporary state-of-the-art

Spatial distribution of natural disasters (wildfires) (Multi-temporal analysis of forest fire probability using socio-economic and environmental variables 2023; Kuter et al. 2011; Big data integration shows Australian bush-fire frequency is increasing significantly 2023)

Prediction of wildfire occurrences

ML models: RF, logistic regression, NNs, SVM

- Address non-linearities in spatial simulation

- Enhanced forecast accuracy Expedited data processing

No

Integration of ML with GIS (Eskandari et al. 2021; Jaafari et al. 2019)

Wildfire mapping sensitivity

ML algorithms with GIS

- Enhanced accuracy

- Faster data processing compared to MCDA

No

Wildfire susceptibility investigation (Comparisons of diverse machine learning approaches for wildfire susceptibility mapping 2023)

Accurate prediction of wildfire susceptibility

Statistical and ML models: NN, RF, SVM, least angle regression, radial basis function, and logistic regression

- High level of accuracy (RF model: 88% AUC)

No

Wildfire risk correlation study (Forest fire susceptibility prediction based on machine learning models with resampling algorithms on remote sensing data 2023)

Correlation analysis

ML models

- Significant correlation findings with human-related variables

No

Wildfire susceptibility mapping (Kalantar et al. 2020)

Mapping wildfire susceptibility

ML techniques: multivariate adaptive regression splines, SVM, boosted regression tree

- Utilization of 14 pivotal indicators influencing wildfires

No

Advanced machine learning in remote sensing (Naderpour et al. 2021; Bjånes et al. 2021)

Wildfire susceptibility prediction

Deep L = learning models (DLs)

- High accuracy (AUC score of 95.3%)

No

Wildfire risk assessment in Sydney (Naderpour et al. 2021)

Evaluating vulnerability of forests to fire

Deep learning model

- Exceptional accuracy with the use of 36 essential variables

No