The “Forest Fires Prediction and Detection” edition highlights the importance of research on fires worldwide. In recent years, the increased frequency of fires caused by climate change has rendered the planet uninhabitable. Several works have been prepared and published in an effort to raise awareness among civil society and government bodies about the importance of developing new technologies for monitoring areas prone to mega-fires. This special issue includes nine important works from various countries. The goal is to better understand the impacts on the world’s most diverse regions, ecosystems, and forest phytophysiognomies. New geotechnologies and fire models were used, both of which are important and could be used in the future to improve short- and long-term planning in firefighting. Full article

The boreal forest of northwestern North America covers an extensive area, contains vast amounts of carbon in its vegetation and soil, and is characterized by extensive wildfires. Catastrophic crown fires in these forests are fueled predominantly by only two evergreen needle-leaf tree species, black spruce (Picea mariana (Mill.) B.S.P.) and lodgepole pine (Pinus contorta Dougl. ex Loud. var. latifolia Engelm.). Identifying where these flammable species grow through time in the landscape is critical for understanding wildfire risk, damages, and human exposure. Because medium resolution landcover data that include species detail are lacking, we developed a compound modeling approach that enabled us to refine the available evergreen forest category into highly flammable species and less flammable species. We then expanded our refined landcover at decadal time steps from 1984 to 2014. With the aid of an existing burn model, FlamMap, and simple succession rules, we were able to predict future landcover at decadal steps until 2054. Our resulting land covers provide important information to communities in our study area on current and future wildfire risk and vegetation changes and could be developed in a similar fashion for other areas. Full article

Assessing and predicting forest fires has long been an arduous task. Nowadays, the rapid advancement of artificial intelligence and machine learning technologies have provided a novel solution to forest fire occurrence assessment and prediction. In this research, we developed a novel hybrid machine-learning-technique algorithm to improve forest fire prediction based on random forest (RF), gradient-boosting decision tree (GBDT), support vector machine (SVM), and other machine learning models. The dataset we employed was satellite fire point data from 2010 to 2018 from the Chinese Department of Fire Prevention. The efficacy and performance of our methods were examined by validating the model fit and predictive capability. The results showed that the ensemble model LR (logistic regression)-RF-SVM-GBDT outperformed the single RFSVMGBDT model and the LR-RF-GBDT integrated framework, displaying higher accuracy and greater robustness. We believe that our newly developed hybrid machine-learning algorithm has the potential to improve the accuracy of predicting forest fire occurrences, thus enabling more efficient firefighting efforts and saving time and resources. Full article

Fire is one of the natural agents with the greatest impact on the terrestrial ecosystem and plays an important ecological role in a large part of the terrestrial surface. Remote sensing is an important technique applied in mapping and monitoring changes in forest landscapes affected by fires. This study presents a spectral separability analysis for the detection of burned areas using Landsat-8 OLI/TIRS images in the context of fires that occurred in different biomes of Brazil (dry ecosystem) and Portugal (temperate forest). The research is based on a fusion of spectral indices and automatic classification algorithms scientifically proven to be effective with as little human interaction as possible. The separability index (M) and the Reed–Xiaoli automatic anomaly detection classifier (RXD) allowed the evaluation of the spectral separability and the thematic accuracy of the burned areas for the different spectral indices tested (Burn Area Index (BAI), Normalized Burn Ratio (NBR), Mid-Infrared Burn Index (MIRBI), Normalized Burn Ratio 2 (NBR2), Normalized Burned Index (NBI), and Normalized Burn Ratio Thermal (NBRT)). The analysis parameters were based on spatial dispersion with validation data, commission error (CE), omission error (OE), and the Sørensen–Dice coefficient (DC). The results indicated that the indices based exclusively on the SWIR1 and SWIR2 bands showed a high degree of separability and were more suitable for detecting burned areas, although it was observed that the characteristics of the soil affected the performance of the indices. The classification method based on bitemporal anomalous changes using the RXD anomaly proved to be effective in increasing the burned area in terms of temporal alteration and performing unsupervised detection without relying on the ground truth. On the other hand, the main limitations of RXD were observed in non-abrupt changes, which is very common in fires with low spectral signal, especially in the context of using Landsat-8 images with a 16-day revisit period. The results obtained in this work were able to provide critical information for fire mapping algorithms and for an accurate post-fire spatial estimation in dry ecosystems and temperate forests. The study presents a new comparative approach to classify burned areas in dry ecosystems and temperate forests with the least possible human interference, thus helping investigations when there is little available data on fires in addition to favoring a reduction in fieldwork and gross errors in the classification of burned areas. Full article

In order to locate forest fire smoke more precisely and expand existing forest fire monitoring methods, this research employed Himawari-8 data with a sub-pixel positioning concept in smoke detection. In this study, Himawari-8 data of forest fire smoke in Xichang and Linzhi were selected. An improved sub-pixel mapping method based on random forest results was proposed to realize the identification and sub-pixel positioning of smoke. More spatial details of forest fire smoke were restored in the final results. The continuous monitoring of smoke indicated the dynamic changes therein. The accuracy evaluation of smoke detection was realized using a confusion matrix. Based on the improved sub-pixel mapping method, the overall accuracies were 87.95% and 86.32%. Compared with the raw images, the smoke contours of the improved sub-pixel mapping results were clearer and smoother. The improved sub-pixel mapping method outperforms traditional classification methods in locating smoke range. Moreover, it especially made a breakthrough in the limitations of the pixel scale and in realizing sub-pixel positioning. Compared with the results of the classic PSA method, there were fewer “spots” and “holes” after correction. The final results of this study show higher accuracies of smoke discrimination, with it becoming the basis for another method of forest fire monitoring. Full article

Deep neural networks (DNNs) have driven the recent advances in fire detection. However, existing methods require large-scale labeled samples to train data-hungry networks, which are difficult to collect and even more laborious to label. This paper applies unsupervised domain adaptation (UDA) to transfer knowledge from a labeled public fire dataset to another unlabeled one in practical application scenarios for the first time. Then, a transfer learning benchmark dataset called Fire-DA is built from public datasets for fire recognition. Next, the Deep Subdomain Adaptation Network (DSAN) and the Dynamic Adversarial Adaptation Network (DAAN) are experimented on Fire-DA to provide a benchmark result for future transfer learning research in fire recognition. Finally, two transfer tasks are built from Fire-DA to two public forest fire datasets, the aerial forest fire dataset FLAME and the large-scale fire dataset FD-dataset containing forest fire scenarios. Compared with traditional handcrafted feature-based methods and supervised CNNs, DSAN reaches 82.5% performance of the optimal supervised CNN on the testing set of FLAME. In addition, DSAN achieves 95.8% and 83.5% recognition accuracy on the testing set and challenging testing set of FD-dataset, which outperform the optimal supervised CNN by 0.5% and 2.6%, respectively. The experimental results demonstrate that DSAN achieves an impressive performance on FLAME and a new state of the art on FD-dataset without accessing their labels during training, a fundamental step toward unsupervised forest fire recognition for industrial applications. Full article

Forest fires are considered one of the major dangers and environmental issues across the world. In the Cerrado biome (Brazilian savannas), forest fires have several consequences, including increased temperature, decreased rainfall, genetic depletion of natural species, and increased risk of respiratory diseases. This study presents a methodology that uses data from the Sea and Land Surface Temperature Radiometer (SLSTR) sensor of the Sentinel-3B satellite and the Moderate Resolution Imaging Spectroradiometer (MODIS) of the Terra satellite to analyze the thematic accuracy of burned area maps and their sensitivity under different spectral resolutions in a large area of 32,000 km² in the Cerrado biome from 2019 to 2021. The methodology used training and the Support Vector Machine (SVM) classifier. To analyze the spectral peculiarities of each orbital platform, the Transformed Divergence (TD) index separability statistic was used. The results showed that for both sensors, the near-infrared (NIR) band has an essential role in the detection of the burned areas, presenting high separability. Overall, it was possible to observe that the spectral mixing problems, registration date, and the spatial resolution of 500 m were the main factors that led to commission errors ranging between 15% and 72% and omission errors between 51% and 86% for both sensors. This study showed the importance of multispectral sensors for monitoring forest fires. It was found, however, that the spectral resolution and burning date may gradually interfere with the detection process. Full article

The technologies and models based on machine vision are widely used for early wildfire detection. Due to the broadness of wild scene and the occlusion of the vegetation, smoke is more easily detected than flame. However, the shapes of the smoke blown by the wind change constantly and the smoke colors from different combustors vary greatly. Therefore, the existing target detection networks have limitations in detecting wildland fire smoke, such as low detection accuracy and high false alarm rate. This paper designs the attention model Recursive Bidirectional Feature Pyramid Network (RBiFPN for short) for the fusion and enhancement of smoke features. We introduce RBiFPN into the backbone network of YOLOV5 frame to better distinguish the subtle difference between clouds and smoke. In addition, we replace the classification head of YOLOV5 with Swin Transformer, which helps to change the receptive fields of the network with the size of smoke regions and enhance the capability of modeling local features and global features. We tested the proposed model on the dataset containing a large number of interference objects such as clouds and fog. The experimental results show that our model can detect wildfire smoke with a higher performance than the state-of-the-art methods. Full article

The occurrence and spread of forest fires are the result of the interaction of many factors. In cross-border areas, different fire management systems may lead to different forest fire driving factors. A comparative analysis of the forest fire driving factors in different countries can help to provide ideas for fire prevention and control. In this study, based on the logistic regression (LR) model and standardized coefficients, we determined the relative impact of forest fire driving factors in different countries, in the cross-border area between China, North Korea and Russia from 2001 to 2020, and established a forest fire probability and fire risk level division using a Kriging interpolation. The results show that the climate is the most important factor affecting the probability of forest fires in the cross-border area, followed by the topography and vegetation factors; human activities have the least influence. From a country-by-country perspective, the forest fires on the Chinese side were more affected by humans than on the North Korean and Russian sides and they were mainly concentrated in areas with a low altitude and high population density. The forest fires on the North Korean side and the Russian side were more affected by nature than on the Chinese side and were mainly concentrated in areas with a low altitude, high temperature and little rainfall. The high-risk areas for forest fires were mostly concentrated near the border between China, North Korea and Russia, where transboundary fires pose a great threat to forest resources and rare animals. This study shows that there is a significant difference between the impact of different forest fire management systems on fire conditions, and that active forest fire control policies can effectively reduce the damage caused by forest fires. Due to the complexity of the geopolitics in cross-border areas, transboundary firefighting faces certain difficulties. In the future, it will be necessary to strengthen the cooperation between countries and establish transboundary joint defenses against forest fires in order to protect the declining forest resources and the habitats of rare animals. Full article

The general objective of this research was to propose a new fire risk index, specifically the Fire Risk Atlantic Forest (FIAF) index in Itatiaia National Park (PNI). The data were collected from two levels (2 and 10 m) of a micrometeorological tower, with a time series on an hourly scale, daily from 2018 to 2021. Two multiple regression models were generated for the two collection levels (FIAF 2 and 10 m) and, based on the statistical criteria and the choice of the best model, a future simulation was generated using the scenario SSP 4.5 for 2022 to 2050. The correlation matrix between the data from the FIAF and fire foci models was also analyzed. The FIAF model was compared with the traditional models already used in Brazil, such as the Angström indices, Monte Alegre Formula (FMA), and the improved Monte Alegre Formula (FMA+) models. The results showed that the FIAF model at 10 m overestimated the results observed mainly during the dry season. The FIAF 2 m model presented the highest correlation with a fire foci value greater than 0.74. In the future simulation, the years that presented the highest extreme risks were: 2025, 2035, 2041, and 2049. Thus, it is possible to state that the FIAF model at the 2 m level was the best model for predicting the degree of fire risk in the PNI. Full article