skip to main content

Title: FIgLib & SmokeyNet: Dataset and Deep Learning Model for Real-Time Wildland Fire Smoke Detection
The size and frequency of wildland fires in the western United States have dramatically increased in recent years. On high-fire-risk days, a small fire ignition can rapidly grow and become out of control. Early detection of fire ignitions from initial smoke can assist the response to such fires before they become difficult to manage. Past deep learning approaches for wildfire smoke detection have suffered from small or unreliable datasets that make it difficult to extrapolate performance to real-world scenarios. In this work, we present the Fire Ignition Library (FIgLib), a publicly available dataset of nearly 25,000 labeled wildfire smoke images as seen from fixed-view cameras deployed in Southern California. We also introduce SmokeyNet, a novel deep learning architecture using spatiotemporal information from camera imagery for real-time wildfire smoke detection. When trained on the FIgLib dataset, SmokeyNet outperforms comparable baselines and rivals human performance. We hope that the availability of the FIgLib dataset and the SmokeyNet architecture will inspire further research into deep learning methods for wildfire smoke detection, leading to automated notification systems that reduce the time to wildfire response.
; ; ; ; ; ; ;
Award ID(s):
Publication Date:
Journal Name:
Remote Sensing
Sponsoring Org:
National Science Foundation
More Like this
  1. Deep-learning (DL)-based object detection algorithms can greatly benefit the community at large in fighting fires, advancing climate intelligence, and reducing health complications caused by hazardous smoke particles. Existing DL-based techniques, which are mostly based on convolutional networks, have proven to be effective in wildfire detection. However, there is still room for improvement. First, existing methods tend to have some commercial aspects, with limited publicly available data and models. In addition, studies aiming at the detection of wildfires at the incipient stage are rare. Smoke columns at this stage tend to be small, shallow, and often far from view, with low visibility. This makes finding and labeling enough data to train an efficient deep learning model very challenging. Finally, the inherent locality of convolution operators limits their ability to model long-range correlations between objects in an image. Recently, encoder–decoder transformers have emerged as interesting solutions beyond natural language processing to help capture global dependencies via self- and inter-attention mechanisms. We propose Nemo: a set of evolving, free, and open-source datasets, processed in standard COCO format, and wildfire smoke and fine-grained smoke density detectors, for use by the research community. We adapt Facebook’s DEtection TRansformer (DETR) to wildfire detection, which results inmore »a much simpler technique, where the detection does not rely on convolution filters and anchors. Nemo is the first open-source benchmark for wildfire smoke density detection and Transformer-based wildfire smoke detection tailored to the early incipient stage. Two popular object detection algorithms (Faster R-CNN and RetinaNet) are used as alternatives and baselines for extensive evaluation. Our results confirm the superior performance of the transformer-based method in wildfire smoke detection across different object sizes. Moreover, we tested our model with 95 video sequences of wildfire starts from the public HPWREN database. Our model detected 97.9% of the fires in the incipient stage and 80% within 5 min from the start. On average, our model detected wildfire smoke within 3.6 min from the start, outperforming the baselines.« less
  2. Due to Wildfire's huge destructive impacts on agriculture and food production, wildlife habitat, climate, human life and ecosystem, timely discovery of fires enable swift response to fires before they go out of control, in order to minimize the resulting damage and impacts. One of the emerging technologies for fire monitoring is deploying Unmanned Aerial Vehicles, due to their high flexibility and maneuverability, less human risk, and on-demand high quality imaging capabilities. In order to realize a real-time system for fire detection and expansion analysis, fast and high-accuracy image-processing algorithms are required. Several studies have shown that deep learning methods can provide the most accurate response, however the training time can be prohibitively long, especially when using online learning for constant refinement of the developed model. Another challenge is the lack of large datasets for training a deep learning algorithm. In this respect, we propose to use a pretrained mobileNetV2 architecture to implement transfer learning, which requires a smaller dataset and reduces the computational complexity while not compromising the accuracy. In addition, we conduct an effective data augmentation pipeline to simulate some extreme scenarios, which could promise the robustness of our approach. The testing results illustrate that our method maintains amore »high identification accuracy in different situations - original dataset (99.7%), adding Gaussian blurred (95.3%), and additive Gaussian noise (99.3%).« less
  3. The objective of this study was to assess feasibility of integrating a coupled fire-atmosphere model within an air-quality forecast system to create a multiscale air-quality modeling framework designed to simulate wildfire smoke. For this study, a coupled fire-atmosphere model, WRF-SFIRE, was integrated, one-way, with the AIRPACT air-quality modeling system. WRF-SFIRE resolved local meteorology, fire growth, the fire plume rise, and smoke dispersion, and provided AIRPACT with fire inputs. The WRF-SFIRE-forecasted fire area and the explicitly resolved vertical smoke distribution replaced the parameterized BlueSky fire inputs used by AIRPACT. The WRF-SFIRE/AIRPACT integrated framework was successfully tested for two separate wildfire events (2015 Cougar Creek and 2016 Pioneer fires). The execution time for the WRF-SFIRE simulations was <3 h for a 48 h-long forecast, suggesting that integrating coupled fire-atmosphere simulations within the daily AIRPACT cycle is feasible. While the WRF-SFIRE forecasts realistically captured fire growth 2 days in advance, the largest improvements in the air quality simulations were associated with the wildfire plume rise. WRF-SFIRE-estimated plume tops were within 300-m of satellite-estimated plume top heights for both case studies analyzed in this study. Air quality simulations produced by AIRPACT with and without WRF-SFIRE inputs were evaluated with nearby PM 2 . 5more »measurement sites to assess the performance of our multiscale smoke modeling framework. The largest improvements when coupling WRF-SFIRE with AIRPACT were observed for the Cougar Creek Fire where model errors were reduced by ∼50%. For the second case (Pioneer fire), the most notable change with WRF-SFIRE coupling was that the probability of detection increased from 16 to 52%.« less
  4. During emergencies communicating in multi-level built environment becomes challenging because architectural complexity can create problems with visual and mental representation of 3D space. Our Hololens application gives a visual representation of a building on campus in 3D space, allowing people to see where exits are in the building as well as creating alerts for anomalous behavior for emergency response such as active shooter, fire, and smoke. It also gives path to the various exits; shortest path to the exits as well as directions to a safe zone from their current position. The augmented reality (AR) application was developed in Unity 3D for Microsoft HoloLens and also is deployed on tablets and smartphones. It is a fast and robust marker detection technique inspired by the use of Vuforia AR library. Our aim is to enhance the evacuation process by ensuring that all building patrons know all of the building exits and how to get to them, which improves evacuation time and eradicates the injuries and fatalities occurring during indoor crises such as building fires and active shooter events. We have incorporated existing permanent features in the building as markers for the AR application to trigger the floor plan and subsequent locationmore »of the person in the building. This work also describes the system architecture as well as the design and implementation of this AR application to leverage HoloLens for building evacuation purposes. We believe that AR technologies like HoloLens could be adopted for all building evacuating strategies during emergencies as it offers a more« less
  5. Viegas, Domingos Xavier (Ed.)
    During the summer of 2015, a number of wildfires fires burned across northern California, which produced significant smoke across the region. Smoke from these wildfires hindered fire-fighting efforts by delaying helicopter operations and exposed communities to high concentrations of atmospheric pollutants. Nighttime inversions are common across the western U.S. and usually mix out during the early afternoon as a result of convective mixing from daytime heating. However, atmospheric conditions in valleys adjacent to the aforementioned wildfires remained stable throughout the afternoon. It is hypothesized that the smoke from nearby wildfires enhanced atmospheric stability due to surface cooling caused by reduced incoming solar radiation, and possibly by warming aloft due to absorption of the incoming solar radiation in the smoke layer. At the same time, mid-level heating from the wildfire could have increased atmospheric stability and extended the duration of the inversion. In this study, we utilize the WRF-SFIRE-CHEM modeling framework, which couples an atmospheric, chemical, and fire spread model in an effort the model the impacts of smoke on local inversions and to improve the physical understanding behind these smoke-induced inversion episodes. This modeling framework was used to simulate the Route and South Complex fires between August 10 – Augustmore »26th, 2015. Preliminary results indicate that wildfire smoke may have significantly reduced incoming solar radiation, leading to local surface cooling by up to 2-3 degrees. Direct heating from the fire itself does not significantly enhance atmospheric stability. However, mid-level warming was observed in the smoke layer suggesting that absorption in this layer may have enhanced the inversion. This study suggests the including the fire-smoke- atmosphere feedbacks in a coupled modeling framework such as WRF-SFIRE-CHEM may help in capturing the impacts of wildfire smoke on near-surface stability and local inversions.« less