A comparative assessment between linear and quadratic discriminant analyses (LDA-QDA) with frequency ratio and weights-of-evidence models for forest fire susceptibility mapping in China

A Hybrid GIS and AHP Approach for Modelling Actual and Future Forest Fire Risk Under Climate Change Accounting Water Resources Attenuation Role

“…The presence of perennial rivers and springs also contributes to decreasing FFR in these areas. Contrary to Hong et al [21,73], You et al [25], and Amalina et al [14], according to whom a higher risk was associated with a minor distance to water courses and springs, in this work, the opposite scenario has been taken in consideration. Usually, the distance from rivers and springs belongs to the anthropogenic factor and it is thought to negatively influence the occurrence of fire, since the existence of camping sites and holoiday spots where human presence in their proximity could increase the FFR.…”

“…The most applied are physics-based method like FIRETEC [15] and LANDIS-II [16], and statistical methods. The latter are often combined with GIS tools [17,18] and include different methodologies, such as multiple linear and logistic regression [11,19,20], fuzzy logic, and weight of evidence [21] among others. Each one of these methodologies suffers from some problems, e.g., physical methods can simulate potential fire behavior through a set of mathematical equations, but are more suitable for small areas, because they require very detailed information.…”

Application of the Artificial Neural Network and Support Vector Machines in Forest Fire Prediction in the Guangxi Autonomous Region, China

“…With the continuous development of artificial intelligence technology, the use of machine learning algorithms to build forest fire prediction models has drawn increasing attention from the scientific community [18][19][20][21][22][23][24][25][26]. Artificial neural networks are a highly nonlinear dynamic system, which can approximate and simulate any nonlinear function of nonlinear dynamic phenomena such as forest fires with strong fault tolerances [27].…”

Landslide Susceptibility Evaluation Using Hybrid Integration of Evidential Belief Function and Machine Learning Techniques

“…The results showed that the RSCART model is the optimal model with the highest AUC values of 0.852 and 0.827, followed by LR and CART models. The results also illustrate that the hybrid model generally improves the prediction ability of a single landslide susceptibility model.Water 2020, 12, 113 2 of 29 weights of evidence [10][11][12], frequency ratio [13][14][15][16][17], logistic regression [18][19][20][21], linear multivariate regression, multivariate adaptive regression spline [22][23][24], and statistical index [25,26] have been widely used. However, these traditional statistical methods do not provide satisfactory evaluation of the correlation between landslide influencing factors [4,27].Therefore, machine learning technologies have drawn extensive attention, and many kinds of machine learning methods have been developed and used, such as classification and regression trees [28,29], adaptive neuro-fuzzy inference systems [30,31], fuzzy logic [32,33], alternating decision trees [34][35][36], support vector machine [37][38][39], artificial neural networks [40,41], and random forest [4,[42][43][44][45].…”

“…Water 2020, 12, 113 2 of 29 weights of evidence [10][11][12], frequency ratio [13][14][15][16][17], logistic regression [18][19][20][21], linear multivariate regression, multivariate adaptive regression spline [22][23][24], and statistical index [25,26] have been widely used. However, these traditional statistical methods do not provide satisfactory evaluation of the correlation between landslide influencing factors [4,27].…”