Forest fires are still a large concern in several countries due to the social, environmental and economic damages caused. This paper aims to show the design and validation of a proposed system for the classification of smoke columns with object detection and a deep learning-based approach. This approach is able to detect smoke columns visible below or above the horizon. During the dataset labelling, the smoke object was divided into three different classes, depending on its distance to the horizon, a cloud object was also added, along with images without annotations. A comparison between the use of RetinaNet and Faster R-CNN was also performed. Using an independent test set, an F1-score around 80%, a G-mean around 80% and a detection rate around 90% were achieved by the two best models: both were trained with the dataset labelled with three different smoke classes and with augmentation; Faster R-CNNN was the model architecture, re-trained during the same iterations but following different learning rate schedules. Finally, these models were tested in 24 smoke sequences of the public HPWREN dataset, with 6.3 min as the average time elapsed from the start of the fire compared to the first detection of a smoke column.

Governmental offices are still highly concerned with controlling the escalation of forest fires due to their social, environmental and economic consequences. This paper presents new developments to a previously implemented system for the classification of smoke columns with object detection and a deep learning-based approach. The study focuses on identifying and correcting several False Positive cases while only obtaining a small reduction of the True Positives. Our approach was based on using an instance segmentation algorithm to obtain the shape, color and spectral features of the object. An ensemble of Machine Learning (ML) algorithms was then used to further identify smoke objects, obtaining a removal of around 95% of the False Positives, with a reduction to 88.7% (from 93.0%) of the detection rate on 29 newly acquired daily sequences. This model was also compared with 32 smoke sequences of the public HPWREN dataset and a dataset of 75 sequences attaining 9.6 and 6.5 min, respectively, for the average time elapsed from the fire ignition and the first smoke detection.

Fires are an important factor in shaping Earth's ecosystems. Plant and animal life, in almost every land habitat, are at least partially dependent on the effects of fire. However, their destructive force, which has often proven uncontrollable, is one of our greatest concerns, effectively resulting in several policies in the most important industrialised regions of the globe. This paper aims to comprehensively characterise the Forest Fire Finder (FFF), a forest fire detection system based mainly upon a spectroscopic technique called differential optical absorption spectroscopy (DOAS). The system is designed and configured with the goal of detecting higher-than-the-horizon smoke columns by measuring and comparing scattered sunlight spectra. The article covers hardware and software, as well as their interactions and specific algorithms for day mode operation. An analysis of data retrieved from several installations deployed in the course of the last 5 years is also presented. Finally, this paper features a discussion on the most prominent future improvements planned for the system, as well as its ramifications and adaptations, such as a thermal imaging system for short-range fire seeking or environmental quality control.

With increasing wildfire severity and duration driven by climate change, accurately predicting fire behavior over extended time frames is critical for effective management and mitigation of such wildfires. Fire propagation models play a pivotal role in these efforts, providing simulations that can be used to strategize and respond to active fires. This study examines the fire area simulator (FARSITE) model’s performance in simulating recent wildfire events that persisted over 24 h with limited firefighting intervention in mostly remote access areas across diverse ecosystems. Our findings reveal key insights into a prolonged wildfire scenarios potentially informing improvements in operational fire management and long-term predictive accuracy, as the area comparisons indexes showed reasonable results between the detected fires from the fire information for resource management systems (FIRMSs) in the first 24 h of the fire and the following days. A case study of a recent wildfire in Madeira Island highlights the integration of real-time weather predictions and post-event weather data analysis. This analysis underscores the potential of combining accurate forecasts with retrospective validation to improve predictive capabilities in dynamic fire environments, which guided the development of a software platform designed to analyse ongoing wildfire events in real-time, leveraging image satellite data and weather predictions.

TomoSim comes as part of project ATMOS, a miniaturised Differential Optical Absorption Spectroscopy (DOAS) tomographic atmospheric evaluation device, designed to fit a small drone. During the development of the project, it became necessary to write a simulation tool for system validation. TomoSim is the answer to this problem. The software has two main goals: to mathematically validate the tomographic acquisition method; and to allow some adjustments to the system before reaching final product stages. This measurement strategy was based on a drone performing a sequential trajectory and gathering projections arranged in fan beams, before using some classical tomographic methods to reconstruct a spectral image. The team tested three different reconstruction algorithms, all of which were able to produce an image, validating the team’s initial assumptions regarding the trajectory and acquisition strategy. All algorithms were assessed on their computational performance and their ability for reconstructing spectral “images”, using two phantoms, one of which custom made for this purpose. In the end, the team was also able to uncover certain limitations of the TomoSim approach that should be addressed before the final stages of the system.