Search Results (81)

Underestimation of PM_2.5 emissions from the agricultural sector persists as a major difficulty for air quality studies, partly because of underutilization of high-resolution observation platforms for constructing a global emissions inventory. Coarse-resolution products used for such purposes often miss fine-scale burnt areas created by stubble-burning practices, which are primary sources of agricultural PM_2.5 emissions. For this study, we used the high-resolution Sentinel-2 observations to examine the spatiotemporal variability of burnt areas in Punjab, a major hotspot of agricultural burning in India, during the post-monsoon fire season (October–December) in 2022–2024. The results highlight the Sentinel-2 capability of detecting more than 34,000 km² of burnt areas (approx. 68% of Punjab’s total area) as opposed to the less than 7000 km² (approx. 12% of Punjab’s total area) detected by MODIS. The study also reveals, in unprecedented detail, multi-annual spatial and temporal shifting of burning events from northern to central and southern Punjab. This detection discrepancy has led to marked disparities in estimated monthly emissions, with approximately 217.3 million tons of PM_2.5 emitted in October 2022 compared to 8.7 million tons found by EDGAR v.8.1. This underscores higher-resolution observation systems intended to support construction of a global PM_2.5 emissions inventory. Full article

Fire occurs naturally and anthropogenically in the Cerrado biome, influenced by hydrology, climate, topography, and land use. Mapping burned areas is essential for understanding the causes of fire and improving prevention and regulation. However, fire scars are often confused with bare soil in agricultural regions. This study presents a method for mapping burned areas using spectral indices and artificial neural networks (ANN). We evaluated the accuracy of these techniques and identified the best input variables for scar detection. Using Sentinel-2 images from 2018 to 2021 during dry periods, we applied NDVI, SAVI, NBR, and CSI indices. The study included two stages: first, finding optimal classification configurations for fire scars, and second, mapping land use and cover with fire scars and crops. Results showed that using all Sentinel-2 bands and the four indices post-fire achieved over 93.7% accuracy and a kappa index of 0.92. Fire scars were mainly located in areas with temporary crops like soybean, sugarcane, rice, and cotton. This low-cost method allows for effective monitoring of fire scars, underscoring the need to regulate agricultural practices in the Cerrado, where burning poses environmental and health risks. Full article

The red imported fire ant (RIFA; Solenopsis invicta) is an invasive species that severely threatens ecology, agriculture, and public health in Taiwan. In this study, the feasibility of applying multispectral imagery captured by unmanned aerial vehicles (UAVs) to detect red fire ant mounds was evaluated in Fenlin Township, Hualien, Taiwan. A DJI Phantom 4 multispectral drone collected reflectance in five bands (blue, green, red, red-edge, and near-infrared), derived indices (normalized difference vegetation index, NDVI, soil-adjusted vegetation index, SAVI, and photochemical pigment reflectance index, PPR), and textural features. According to analysis of variance F-scores and random forest recursive feature elimination, vegetation indices and spectral features (e.g., NDVI, NIR, SAVI, and PPR) were the most significant predictors of ecological characteristics such as vegetation density and soil visibility. Texture features exhibited moderate importance and the potential to capture intricate spatial patterns in nonlinear models. Despite limitations in the analytics, including trade-offs related to flight height and environmental variability, the study findings suggest that UAVs are an inexpensive, high-precision means of obtaining multispectral data for RIFA monitoring. These findings can be used to develop efficient mass-detection protocols for integrated pest control, with broader implications for invasive species monitoring. Full article

Since 2020, the Gs/Gd H5N1 influenza virus (clade 2.3.4.4b) has established itself within wild bird populations across Asia, Europe, and the Americas, causing outbreaks in wild mammals, commercial poultry, and dairy farms. The impacts on the bird populations and the agricultural industry has been significant, requiring a One Health approach to enhanced surveillance in both humans and animals. To support pandemic preparedness efforts, we evaluated the Cepheid Xpert Xpress CoV-2/Flu/RSV plus kit and the BioFire Respiratory 2.1 Panel for their ability to detect the presence of non-seasonal, zoonotic influenza A viruses, including circulating H5N1 viruses from clade 2.3.4.4b. Both assays effectively detected the presence of influenza virus in clinically-contrived nasal swab and saliva specimens at low concentrations. The results generated using the Cepheid Xpert Xpress CoV-2/Flu/RSV plus kit and the BioFire Respiratory 2.1 Panel, in conjunction with clinical and epidemiological findings provide valuable diagnostic findings that can strengthen pandemic preparedness and surveillance initiatives. Full article

The use of Google Earth Engine (GEE), a cloud-based computing platform, in spatio-temporal evaluation studies has increased rapidly in natural sciences such as forestry. In this study, Sentinel-2 satellite imagery and Shuttle Radar Topography Mission (SRTM) elevation data and image classification algorithms based on two machine learning techniques were examined. Random Forest (RF) and Classification and Regression Trees (CART) were used to classify land use and land cover (LULC) in western Oregon (USA). To classify the LULC from the spectral bands of satellite images, a composition consisting of vegetation difference indices NDVI, NDWI, EVI, and BSI, and a digital elevation model (DEM) were used. The study area was selected due to a diversity of land cover types including research forest, botanical gardens, recreation area, and agricultural lands covered with diverse plant species. Five land classes (forest, agriculture, soil, water, and settlement) were delineated for LULC classification testing. Different spatial points (totaling 75, 150, 300, and 2500) were used as training and test data. The most successful model performance was RF, with an accuracy of 98% and a kappa value of 0.97, while the accuracy and kappa values for CART were 95% and 0.94, respectively. The accuracy of the generated LULC maps was evaluated using 500 independent reference points, in addition to the training and testing datasets. Based on this assessment, the RF classifier that included elevation data achieved an overall accuracy of 92% and a kappa coefficient of 0.90. The combination of vegetation difference indices with elevation data was successful in determining the areas where clear-cutting occurred in the forest. Our results present a promising technique for the detection of forests and forest openings, which was helpful in identifying clear-cut sites. In addition, the GEE and RF classifier can help identify and map storm damage, wind damage, insect defoliation, fire, and management activities in forest areas. Full article

Woody plant encroachment (WPE) is transforming grasslands globally, yet accurately mapping this process remains challenging. State-funded, publicly available high-resolution aerial imagery offers a potential solution, including the USDA’s National Agriculture Imagery Program (NAIP) and NSF’s National Ecological Observatory Network (NEON) Aerial Observation Platform (AOP). We evaluated the accuracy of land cover classification using NAIP, NEON, and both sources combined. We compared two machine learning models—support vector machines and random forests—implemented in R using large training and evaluation data sets. Our study site, Konza Prairie Biological Station, is a long-term experiment in which variable fire and grazing have created mosaics of herbaceous plants, shrubs, deciduous trees, and evergreen trees (Juniperus virginiana). All models achieved high overall accuracy (>90%), with NEON slightly outperforming NAIP. NAIP underperformed in detecting evergreen trees (52–78% vs. 83–86% accuracy with NEON). NEON models relied on LiDAR-based canopy height data, whereas NAIP relied on multispectral bands. Combining data from both platforms yielded the best results, with 97.7% overall accuracy. Vegetation indices contributed little to model accuracy, including NDVI (normalized digital vegetation index) and EVI (enhanced vegetation index). Both machine learning methods achieved similar accuracy. Our results demonstrate that free, high-resolution imagery and open-source tools can enable accurate, high-resolution, landscape-scale WPE monitoring. Broader adoption of such approaches could substantially improve the monitoring and management of grassland biodiversity, ecosystem function, ecosystem services, and environmental resilience. Full article

Unmanned aerial vehicles, also termed as unarmed aerial vehicles, are used for various purposes in and around the environment, such as delivering things, spying on opponents, identification of aerial images, extinguishing fire, spraying the agricultural fields, etc. As there are multi-functions in a single UAV model, it can be used for various purposes as per the user’s requirement. The UAVs are used for faster communication of identified information, entry through the critical atmospheres, and causing no harm to humans before entering a collapsed path. In relation to the above discussion, a UAV system is designed to classify and transmit information about the atmospheric conditions of the environment to a central controller. The UAV is equipped with advanced sensors that are capable of detecting air pollutants such as carbon monoxide (CO), carbon dioxide (CO₂), methane (CH₄), ammonia (NH₃), hydrogen sulfide (H₂S), etc. These sensors present in the UAV model monitor the quality of air, time-to-time, as the UAV navigates through different areas and transmits real-time data regarding the air quality to a central unit; this data includes detailed information on the concentrations of different pollutants. The central unit analyzes the data that are captured by the sensor and checks whether the quality of air meets the atmospheric standards. If the sensed levels of pollutants exceed the thresholds, then the system present in the UAV triggers a warning alert; this alert is communicated to local authorities and the public to take necessary precautions. The developed UAV is furnished with cameras which are used to capture real-time images of the environment and it is processed using the YOLO V3 algorithm. Here, the YOLO V3 algorithm is defined to identify the context and source of pollution, such as identifying industrial activities, traffic congestion, or natural sources like wildfires. Full article

In recent years, agricultural landscapes have increasingly suffered from severe fire incidents, posing significant threats to crop production, economic stability, and environmental sustainability. Timely and precise detection of fires, especially at their incipient stages, remains crucial to mitigate damage and prevent ecological degradation. However, conventional detection methods frequently fall short in accurately identifying small-scale fire outbreaks due to limitations in sensitivity and response speed. Addressing these challenges, this research proposes an advanced fire detection model based on a modified Detection Transformer (DETR) architecture. The proposed framework incorporates an optimized ConvNeXt backbone combined with a novel Feature Enhancement Block (FEB), specifically designed to refine spatial and contextual feature representation for improved detection performance. Extensive evaluations conducted on a carefully curated agricultural fire dataset demonstrate the effectiveness of the proposed model, achieving precision, recall, mean Average Precision (mAP), and F1-score of 89.67%, 86.74%, 85.13%, and 92.43%, respectively, thereby surpassing existing state-of-the-art detection frameworks. These results validate the proposed architecture’s capability for reliable, real-time identification, offering substantial potential for enhancing agricultural resilience and sustainability through improved preventive strategies. Full article

Agricultural fires significantly threaten global food systems, ecosystems, and rural economies, necessitating timely detection to prevent widespread damage. This study presents a lightweight and enhanced version of the YOLOv5s model, optimized for early-stage agricultural fire detection. The core innovation involves deepening the C3 block and integrating DarknetBottleneck modules to extract finer visual features from subtle fire indicators such as light smoke and small flames. Experimental evaluations were conducted on a custom dataset of 3200 annotated agricultural fire images. The proposed model achieved a precision of 88.9%, a recall of 85.7%, and a mean Average Precision (mAP) of 87.3%, outperforming baseline YOLOv5s and several state-of-the-art (SOTA) detectors such as YOLOv7-tiny and YOLOv8n. The model maintains a compact size (7.5 M parameters) and real-time capability (74 FPS), making it suitable for resource-constrained deployment. Our findings demonstrate that focused architectural refinement can significantly improve early fire detection accuracy, enabling more effective response strategies and reducing agricultural losses. Full article

Solar-powered unmanned aerial vehicles are fixed-wing aircraft designed to operate solely on solar power. Their defining feature is an advanced power system that uses solar cells to absorb sunlight during the day and convert it into electrical energy. Excess energy generated during flight can be stored in batteries, ensuring uninterrupted operation day and night. By harnessing the power of the sun, these aircraft offer key benefits such as extended flight endurance, reduced dependence on fossil fuels, and cost efficiency improvements. As a result, they have attracted considerable attention in a variety of military and civil applications, including surveillance, environmental monitoring, agriculture, communications, weather monitoring, and fire detection. This review presents selected aspects of the development and use of solar-powered aircraft. First, the general classification of unmanned aerial vehicles is presented. Then, the design process of solar-powered unmanned aerial vehicles is discussed, including issues such as the structure and materials used in solar-powered aircraft, the integration of solar cells into the wings, the selection of appropriate battery technologies, and the optimization of energy management to ensure their efficient and reliable operation. General information on the above areas is supplemented by the presentation of results discussed in the selected literature sources. Finally, the practical applications of solar-powered aircraft are discussed, with examples including surveillance, environmental monitoring, agriculture, and wildfire detection. The work is summarized via a discussion of the future research directions for the development of solar-powered aircraft. The review is intended to motivate further work focusing on the widespread use of clean, efficient, and environmentally friendly unmanned aerial vehicles for various applications. Full article

The increasing frequency and severity of agricultural fires pose significant threats to food security, economic stability, and environmental sustainability. Traditional fire-detection methods, relying on satellite imagery and ground-based sensors, often suffer from delayed response times and high false-positive rates, limiting their effectiveness in mitigating fire-related damages. In this study, we propose an advanced deep learning-based fire-detection framework that integrates the Single-Shot MultiBox Detector (SSD) with the computationally efficient MobileNetV2 architecture. This integration enhances real-time fire- and smoke-detection capabilities while maintaining a lightweight and deployable model suitable for Unmanned Aerial Vehicle (UAV)-based agricultural monitoring. The proposed model was trained and evaluated on a custom dataset comprising diverse fire scenarios, including various environmental conditions and fire intensities. Comprehensive experiments and comparative analyses against state-of-the-art object-detection models, such as You Only Look Once (YOLO), Faster Region-based Convolutional Neural Network (Faster R-CNN), and SSD-based variants, demonstrated the superior performance of our model. The results indicate that our approach achieves a mean Average Precision (mAP) of 97.7%, significantly surpassing conventional models while maintaining a detection speed of 45 frames per second (fps) and requiring only 5.0 GFLOPs of computational power. These characteristics make it particularly suitable for deployment in edge-computing environments, such as UAVs and remote agricultural monitoring systems. Full article

High-resolution Sentinel-2 imagery combined with a deep learning (DL) segmentation model offers a promising approach for accurate mapping of small and fragmented agricultural burn areas. Initially, the model was trained using ICNF burn area data from Portugal to capture large fire and burn area delineation, thereby achieving moderate accuracy. Subsequent fine-tuning using annotated data from Punjab improved the model’s ability to detect small burn patches, demonstrating higher accuracy than the baseline Normalized Burn Ratio (NBR) Index method. On-ground validation using buffer zone analysis and crop field images confirmed the effectiveness of DL approach. Challenges such as cloud interference, temporal gaps in satellite data, and limited reference data for training persist, but this study underscores the methodogical advancements and potential of DL models applied for small burn area detection in agricultural settings. The model achieved overall accuracy of 98.7%, a macro-F1 score of 97.6%, IoU 0.54, and a Dice coefficient of 0.64, demonstrating its capability for detailed burn area delineation. The model can capture burn area smaller than 250 m², but the model at present is less efficient at representing the full extent of the fires. Overall, outcomes demonstrate the model’s applicability to generalize to a new domain despite regional differences among research areas. Full article

This study addresses the task of ecologically assessing the consequences of natural fires. Statistical data are presented on the carbon dioxide emissions in millions of tons and analytical data on the locations of peat fires, as well as modern methods of detection and control of peat and forest fires, divided into groups. An analysis of the works of leading Russian and international scientists and research organizations engaged in the search for methods of peat fire forecasting is also presented. Our aim was to develop a more effective method of preventing peat soil ignition by changing its physical and moisture characteristics. To that end, peat samples were selected in the Tver region. The laboratory equipment and the methodology of our experimental studies are described in detail, in which we simulated the natural climatic conditions in the center of the Russian Federation. This study provides a mathematical description of the process of spontaneous ignition, which occurs according to the following steps: a heat flow heats the surface to the ignition temperature, creating a self-heating zone; eventually, a wave of ignition (smoldering) capable of self-propagation is formed. We experimentally determined the spontaneous thermal ignition conditions in our experimental studies of the fire hazards of selected peat samples, where the test material was loaded in a cylindrical container made of brass net with a 0.8 mm mesh, of the dimensions 30 × 30 mm. Thermocouple elements were placed inside the container, fixing the temperature of the surface and the center of the sample, where the smoldering or ignition zone of the test material formed. We analyzed the results of our experimental studies on peat samples’ self-heating chemical reaction, leading us to draw conclusions about the possibility of fires on peat soil depending on its physical and chemical characteristics. We also offer recommendations that will improve peat soils’ fire safety, permitting agricultural crop production without a peat fire risk. Full article

The use of wireless sensor networks (WSNs) in critical applications such as environmental monitoring, smart agriculture, and industrial automation has created significant security concerns, particularly due to the broadcasting nature of wireless communication. The absence of physical-layer authentication mechanisms exposes these networks to threats like spoofing, compromising data authenticity. This paper introduces a multi-attribute physical layer authentication (PLA) scheme to enhance WSN security by using physical attributes such as received signal strength indicator (RSSI), battery level (BL), and altitude. The LoRaWAN join procedure, a key risk due to plain text transmission without encryption during initial communication, is addressed in this study. To evaluate the proposed approach, a partially synthesized dataset was developed. Real-world RSSI values were sourced from the LoRa at the Edge Dataset, while BL and altitude columns were added to simulate realistic sensor behavior in a forest fire detection scenario. Machine learning (ML) models, including Logistic Regression (LR), Random Forest (RF), and K-Nearest Neighbors (KNN), were compared with deep learning (DL) models, such as Multi-Layer Perceptron (MLP) and Convolutional Neural Networks (CNN). The results showed that RF achieved the highest accuracy among machine learning models, while MLP and CNN delivered competitive performance with higher resource demands. Full article

Evidence of unintended introductions of Phytophthora species into native habitats has become increasingly prevalent in California. If not managed adequately, Phytophthora species can become devastating agricultural and forest plant pathogens. Additionally, California’s natural areas, characterized by a Mediterranean climate and dominated by chaparral (evergreen, drought-tolerant shrubs) and oak woodlands, lack sufficient baseline knowledge on Phytophthora biology and ecology, hindering effective management efforts. From 2018 to 2021, soil samples were collected from Angeles National Forest lands (Los Angeles County) with the objective of better understanding the diversity and distribution of Phytophthora species in Southern California. Forty sites were surveyed, and soil samples were taken from plant rhizospheres, riverbeds, and off-road vehicle tracks in chaparral and oak woodland areas. From these surveys, fourteen species of Phytophthora were detected, including P. cactorum (subclade 1a), P. multivora (subclade 2c), P. sp. cadmea (subclade 7a), P. taxon ‘oakpath’ (subclade 8e, first reported in this study), and several clade-6 species, including P. crassamura. Phytophthora species detected in rhizosphere soil were found underneath both symptomatic and asymptomatic plants and were most frequently associated with Salvia mellifera, Quercus agrifolia, and Salix sp. Phytophthora species were present in both chaparral and oak woodland areas and primarily in riparian areas, including detections in off-road tracks, trails, and riverbeds. Although these Mediterranean ecosystems are among the driest and most fire-prone areas in the United States, they harbor a large diversity of Phytophthora species, indicating a potential risk for disease for native Californian vegetation. Full article