Mapping Homogeneous Response Areas for Forest Fuel Management Using Geospatial Data, K-Means, and Random Forest Classification

Abstract

Accurate description of forest fuels is necessary for developing appropriate fire management strategies aimed at reducing fire risk. Although field surveys provide accurate measurements of forest fuel load estimations, they are time consuming, expensive, and may fail to capture the inherent spatial heterogeneity of forest fuels. Previous efforts were carried out to solve this issue by estimating homogeneous response areas (HRAs), representing a promising alternative. However, previous methods suffer from a high degree of subjectivity and are difficult to validate. This paper presents a method, which allows eliminating subjectivity in estimating HRAs spatial distribution, using artificial intelligence machine learning techniques. The proposed method was developed in the natural protected area of “Sierra de Quila,” Jalisco, and was replicated in “Sierra de Álvarez,” San Luis Potosí and “Selva El Ocote,” Chiapas, Mexico, to prove its robustness. Input data encompassed a set of environmental variables including altitude, average annual precipitation, enhanced vegetation index, and forest canopy height. Four, three, and five HRAs with overall accuracy of 97.78%, 98.06%, and 98.92% were identified at “Sierra de Quila,” “Sierra de Álvarez,” and “Selva El Ocote,” respectively. Altitude and average annual precipitation were identified as the most explanatory variables in all locations, achieving a mean decrease in impurity values greater than 52.51% for altitude and up to 36.02% for average annual precipitation. HRAs showed statistically significant differences in all study sites according to the Kruskal–Wallis test (p-value < 0.05). Differences among groups were also significant based on the Wilcoxon–Mann–Whitney (p-value < 0.05) for all variables but EVI in “Selva El Ocote.” These results show the potential of our approach to objectively identify distinct homogeneous areas in terms of their fuel properties. This allows the adequate management of fire and forest fuels in decision-making processes.

Characterizing Forest Fuel Properties and Potential Wildfire Dynamics in Xiuwu, Henan, China

“…Combustible types were categorized by hierarchical cluster analysis. The hierarchical cluster analysis used Euclidean distance as a similarity measure and clustering based on Ward's method [24,25] to standardize the variables of stand density, mean diameter at breast height, mean tree height, tree load, and litter load, and the mean tree height, tree load, and litter load were standardized using the standardized Kruskal-Wallis, and then tested for differences between the variables using the Kruskal-Wallis method [26]. After classifying several combustible types through systematic cluster analysis, the combustible parameters of all the samples within the same type were averaged and assigned to the corresponding combustible type, resulting in a number of combustible types and their attributes, which are represented by a clustered spectrogram (commonly known as a dendrogram).…”

Forest Canopy Fuel Loads Mapping Using Unmanned Aerial Vehicle High-Resolution Red, Green, Blue and Multispectral Imagery

“…The study area is also prone to natural and human disturbances, such as insect outbreaks, firewood production, and timber harvesting. Previous studies have classified the area according to Homogeneous Response Areas (HRAs), where field information collected in situ can be extrapolated to areas with similar characteristics [31].…”

“…The field data utilized in this research belong to the same HRA of the study area, where they share a common ecological background. This context enables in situ data collection to extrapolate to areas with similar characteristics [31]. However, the robustness of the method ensures its replicability across various latitudes.…”

Spatio-Temporal Assessment of Heterogeneity by Logging Intensity in a Federal Concession Area in the Brazilian Amazon

“…To determine the optimal number of clusters (k), the elbow method was employed through visual analysis of the graph. Utilizing the elbow method with k-means clustering in the context of forest analysis is a conventional approach in data science and ecology [60][61][62][63][64]. An evaluation of the dissimilarity of the variables (SSEs) among each cluster was conducted to identify potential heterogeneities in forest exploitation.…”