International journal of applied earth observation and geoinformation : ITC journal最新文献

{"title":"Uncovering the seasonal dynamics of terrestrial oil spills through multi-temporal and multi-frequency Synthetic Aperture radar (SAR) observations","authors":"Mohammed S Ozigis ,&nbsp;Jörg D Kaduk ,&nbsp;Claire H Jarvis ,&nbsp;Polyanna da Conceição Bispo ,&nbsp;Heiko Balzter","doi":"10.1016/j.jag.2024.104286","DOIUrl":"10.1016/j.jag.2024.104286","url":null,"abstract":"<div><div>The phenological characteristics of vegetation exposed to oil pollution can reveal how different vegetation types and species respond to the effects of hydrocarbons in crude oil. This can further inform the recovery status and remediation efforts on polluted sites. In this study, the potential of various SAR frequencies (including multitemporal C band Sentinel-1, X band Cosmo Skymed, X band TanDEM-X, and L band ALOS PALSAR 2) were explored to analyse the characteristics of vegetation affected by hydrocarbons over time. The SAR backscatter characteristics of both oil-polluted and oil-free vegetation were systematically examined across different seasons to deduce the primary effects of oil pollution. Additionally, machine learning random forest (RF) classification and support vector machines (SVM) were implemented on seasonal image composites to assess spatial extent. Results show that stress caused by oil pollution on vegetation is better distinguishable during the wet season in the VV channel than in the VH channel of the multitemporal Sentinel 1. This was supported by the machine learning classification, as overall accuracy (OA) and Kappa (K) were also highest with the wet season SAR image composites. A further incorporation of L- and X-Band multifrequency SAR across the two seasons showed that the wet season composites significantly improved the classification accuracy, with Cropland, Grassland and Tree Cover Area (TCA) recording an increase in OA and K, to 82.3 % and 0.64, 66.67 % and 0.33, and 74.7 % and 0.49, respectively. Findings presented in this study represent a pioneering exploration of the capabilities of multi-temporal and multi-sensor SAR imagery in discriminating oil-impacted from healthy vegetation. This holds significant promise in evaluating the progress of environmental remediation, the regeneration of vegetation, and recovery efforts.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"135 ","pages":"Article 104286"},"PeriodicalIF":7.6,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142747727","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Remotely geolocating static events observed by citizens using data collected by mobile devices","authors":"Jacinto Estima ,&nbsp;Ismael Jesus ,&nbsp;Cidália C. Fonte ,&nbsp;Alberto Cardoso","doi":"10.1016/j.jag.2024.104287","DOIUrl":"10.1016/j.jag.2024.104287","url":null,"abstract":"<div><div>The increasing use of smartphones has led to a surge in crowdsourcing initiatives, where citizens easily collect and upload information using advanced sensors, leveraging the collective efforts of the crowd. However, these devices face accuracy issues that must be addressed before they can be used effectively in certain applications. While most research has focused on GNSS-based positioning errors, compass-based orientation errors have received far less attention. This paper presents a novel method for determining the geolocation of static events by combining contributions from multiple volunteers located around a target event. Instead of straight lines, the method applies funnel-shaped regions to represent the azimuths toward the target location and encompasses various phases to address errors stemming from measured azimuths. These compass-based orientation errors have attracted less attention compared to GNSS-based positioning errors. The approach mitigates the uncertainty in azimuth measurements, producing a set of regions that contain the target location with different levels of confidence. Its reliability was tested in three case studies with known target locations, using metrics such as area and compactness. The results were promising, indicating that the developed approach is particularly useful in applications that do not require a high degree of accuracy (common in many crowdsourcing projects), such as the geolocation of forest fire ignitions − once in the vicinity they can be easily spotted. Implementing this approach within a system that collates citizens’ contributions can furnish invaluable information to authorities, empowering prompt action during emergency scenarios.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"135 ","pages":"Article 104287"},"PeriodicalIF":7.6,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142757682","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Assessing the impact of land cover on air quality parameters in Jordan: A spatiotemporal study using remote sensing and cloud computing (2019–2022)","authors":"Khaled Hazaymeh,&nbsp;Murad Al-Jarrah","doi":"10.1016/j.jag.2024.104293","DOIUrl":"10.1016/j.jag.2024.104293","url":null,"abstract":"<div><div>This study aimed to analyze the spatiotemporal concentration of air pollutants in the tropospheric layer of Jordan, in the Middle East, for 2019–2022. The study utilized remotely sensed data from two satellite systems, Sentinel-5P and Landsat-9, to retrieve information about the concentration of nitrogen dioxide (NO₂), sulfur dioxide (SO₂), and carbon monoxide (CO) and land use types, respectively. The Google Earth Engine (GEE) platform and JavaScript were used to produce monthly short-term average concentration maps and time series for the three pollutants. Pearson correlation analysis was performed to evaluate the performance of Sentinel-5P data against ground-based monitoring stations in estimating NO₂, SO₂, and CO concentration at a regional scale. Results revealed a moderate correlation, with <em>r</em>-values of 0.42, 0.43, and 0.40, for NO₂, SO₂, and CO, respectively. The spatiotemporal analysis showed a higher concentration of SO₂ and NO₂ in the northern and middle regions of the country, coinciding with the spatial distribution of built-up areas and the main urban centers. On a temporal scale, the highest concentration of the three pollutants was observed in the winter months for all governorates of Jordan. For instance, it was found that the highest value of NO₂ was in Balqa Governorate in December 2022, 1.57 * 10^4 mol/m². The highest average monthly SO₂ values were observed in Jerash Governorate in December 2019, 7.36 * 10^4 mol/m². CO concentrations were mainly concentrated in the western parts of the Jordan rift valley.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"135 ","pages":"Article 104293"},"PeriodicalIF":7.6,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142747725","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"PhySoilNet: A deep learning downscaling model for microwave satellite soil moisture with physical rule constraint","authors":"Zhenheng Xu ,&nbsp;Hao Sun ,&nbsp;JinHua Gao ,&nbsp;Yunjia Wang ,&nbsp;Dan Wu ,&nbsp;Tian Zhang ,&nbsp;Huanyu Xu","doi":"10.1016/j.jag.2024.104290","DOIUrl":"10.1016/j.jag.2024.104290","url":null,"abstract":"<div><div>Surface soil moisture (SM) plays an important role in water and energy cycles. Passive microwave remote sensing observation has become the main means of obtaining large-scale surface SM. Due to its low spatial resolution, the spatial downscaling is required. With the development of artificial intelligence, data-driven SM downscaling models have emerged in recent years and have shown better accuracy than traditional physical models. However, data-driven SM downscaling models still have problems such as poor interpretability and easy overfitting. Therefore, this paper proposes a new SM downscaling model based on physical rule-constrained deep learning, named Physics-informed Soil Moisture Downscaling Deep Neural Network (PhySoilNet). This model adds the physical relationship between SM and the downscaling factor Land surface Evaporative Efficiency, as well as the saturated and residual boundary of SM into the Loss function of deep learning, thereby constraining the neural network. Results showed that PhySoilNet successfully downscaled the 9 km Soil Moisture Active Passive (SMAP) SM to 500 m, and performed well in the evaluations with in-situ, aerial, and SMAP SM. Compared to the downscaling model of only data-driven, the PhySoilNet had better performance in all evaluations, and the metrics in the in-situ SM network evaluation were improved by 20 % for R, 9.9 % for ubRMSE, 7.2 % for MAE, and 7.2 % for RMSE. At the same time, the number of SM predicted by PhySoilNet that outside the reasonable SM boundary range was significantly reduced. This fully demonstrates that data-driven based on physical rule constraints can achieve SM downscaling more effectively. Coupling physical rules and deep learning can fully utilize the powerful fitting ability of data-driven methods while improving the generalization ability and interpretability of downscaling models through prior physical knowledge.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"135 ","pages":"Article 104290"},"PeriodicalIF":7.6,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142747729","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Assessing land suitability for leguminous crops in the okavango river basin: A multicriteria and machine learning approach","authors":"Kaleb Gizaw Negussie ,&nbsp;Bisrat Haile Gebrekidan ,&nbsp;Daniel Wyss ,&nbsp;Martin Kappas","doi":"10.1016/j.jag.2024.104284","DOIUrl":"10.1016/j.jag.2024.104284","url":null,"abstract":"<div><div>This study aimed to create a model to identify land suitable for growing sunn hemp (<em>Crotalaria juncea</em>) and pigeon pea (<em>Cajanus cajan</em>) in the Okavango River basin of the Kavango East region of Namibia. Advanced tree-based ensemble learning models, including Random Forest, Extra Trees, Gradient Boosting, XGBoost and multivariate regression analysis , were employed to enhance analytical accuracy. The Random Forest and XGboost models exhibited outstanding performance, as evidenced by their respective accuracy values of 0.97 and 0.96. In addition, this study proposed an innovative approach through the integration of subjective and objective analytical methods, which are independent of one another. The subjective component of the analysis employed a Multi-Criteria Decision Making-Analytic Hierarchy Process (MCDM-AHP). On the other hand, the objective component used a data-driven multivariate approach supported by tree-based learning algorithms. Twenty-two variables were considered, encompassing climatic conditions, hydro-geomorphologic features, soil characteristics, vegetation patterns, and socio-economic factors. These variables played a crucial role to identify the most suitable areas for growing the selected leguminous crops. The MCDM-AHP method utilised expert evaluations to rank the importance of variables, identifying water sources, slope, and soil properties as key factors. A suitability mapping analysis revealed that 17.63% of the area was highly suitable and 62.77% moderately suitable, while 10% was less suitable and 9.59% unsuitable for growing these two legumes. According to the data driven methodology, soil fertility and nitrogen content emerged as key determinants for land suitability. This is particularly relevant for nitrogen-fixing leguminous crops such as sunn hemp and pigeon pea, which play a central role in improving soil quality and ensuring food security.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"135 ","pages":"Article 104284"},"PeriodicalIF":7.6,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142747726","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-temporal remote sensing of inland surface waters: A fusion of sentinel-1&2 data applied to small seasonal ponds in semiarid environments","authors":"Francesco Valerio ,&nbsp;Sérgio Godinho ,&nbsp;Gonçalo Ferraz ,&nbsp;Ricardo Pita ,&nbsp;João Gameiro ,&nbsp;Bruno Silva ,&nbsp;Ana Teresa Marques ,&nbsp;João Paulo Silva","doi":"10.1016/j.jag.2024.104283","DOIUrl":"10.1016/j.jag.2024.104283","url":null,"abstract":"<div><div>Inland freshwaters are essential in maintaining ecological balance and supporting human development. However, comprehensive water data cataloguing remains insufficient, especially for small water bodies (i.e., ponds), which are overlooked despite their ecological importance. To address this gap, remote sensing has emerged as a possible solution for understanding ecohydrological characteristics of water bodies, particularly in water-stressed areas. Here, we propose a novel framework based on a Sentinel-1&amp;2 local surface water (SLSW) model targeting very small (&lt;0.5 ha, <em>Mdn</em> ≈ 0.031 ha) and seasonal water bodies. We tested this framework in three semiarid regions in SW Iberia, subjected to distinct seasonality and bioclimatic changes. Surface water attributes, including surface water occurrence and extent, were modelled using a Random Forests classifier, and SLSW time series forecasts were generated from 2020 to 2021. Model<!--> <!-->reliability was first verified through comparative data completeness analyses with the established Landsat-based global surface water (LGSW) model, considering both intra-annual and inter-annual variations. Further, the performance of the SLSW and LGSW models was compared by examining their correlations for specific periods (dry and wet seasons) and against a validation dataset. The SLSW model demonstrated satisfactory results in detecting surface water occurrence (<em>μ</em> ≈ 72 %), and provided far greater completeness and reconstructed seasonality patterns than the LGSW model. Additionally, SLSW model exhibited a stronger correlation with LGSW during wet seasons (R² = 0.38) than dry seasons (R² = 0.05), and aligned more closely with the validation dataset (R² = 0.66) compared to the LGSW model (R² = 0.24). These findings underscore the SLSW model’s potential to effectively capture surface characteristics of very small and seasonal water bodies, which are challenging to map over broad regions and often beyond the capabilities of conventional global products. Also, given the vulnerability of water resources in semiarid regions to climate fluctuations, the present framework offers advantages for the local reconstruction of continuous, high-resolution time series, useful for identifying surface water trends and anomalies. This information has the potential to better guide regional water management and policy in support of Sustainable Development Goals, focusing on ecosystem resilience and water sustainability.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"135 ","pages":"Article 104283"},"PeriodicalIF":7.6,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142747728","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Back to geometry: Efficient indoor space segmentation from point clouds by 2D–3D geometry constrains","authors":"Shengjun Tang ,&nbsp;Junjie Huang ,&nbsp;Benhe Cai ,&nbsp;Han Du ,&nbsp;Baoding Zhou ,&nbsp;Zhigang Zhao ,&nbsp;You Li ,&nbsp;Weixi Wang ,&nbsp;Renzhong Guo","doi":"10.1016/j.jag.2024.104265","DOIUrl":"10.1016/j.jag.2024.104265","url":null,"abstract":"<div><div>This paper addresses the challenge of indoor space segmentation from 3D point clouds, which is essential for understanding interior layouts, reconstructing 3D structures, and developing indoor navigation maps. While current deep learning-based methods rely on projecting 3D point clouds into 2D for instance extraction, they often fail to capture the local and global 3D features necessary for effectively segmenting complex indoor spaces, such as multi-ring nested structures. These methods also struggle with generalization across different scenes. In response, this paper proposes an efficient indoor space segmentation method that integrates both 2D and 3D geometric constraints. By leveraging the distribution characteristics of point clouds in 2D and the local and global features in 3D, the method achieves reliable extraction of vertical structural information in complex indoor environments. To address under-segmentation in small spaces due to varying scales, the paper introduces an adaptive extraction method for space partition anchors, guided by local features. During instance-level space segmentation, a hierarchical contour tree structure is employed to precisely partition complex indoor spaces, effectively handling circular and composite structures. The proposed approach was tested on 96 RGB-D scans from the Beike dataset and 6 large-scale indoor scenes from the S3DIS dataset, covering a range of complexities, sizes, and structures. The experimental section includes ablation studies and thorough comparisons with existing state-of-the-art spatial partitioning algorithms based on morphology and deep learning. Results demonstrate that the proposed method significantly outperforms existing approaches in terms of accuracy, robustness, and generalization ability, providing a solid foundation for indoor space modeling and robotic navigation. The source code and datasets will be made publicly available via the “<span><span>EISPGeo</span><svg><path></path></svg></span>” link.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"135 ","pages":"Article 104265"},"PeriodicalIF":7.6,"publicationDate":"2024-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142721591","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Fine-scale retrieval of leaf chlorophyll content using a semi-empirically accelerated 3D radiative transfer model","authors":"Xun Zhao ,&nbsp;Jianbo Qi ,&nbsp;Jingyi Jiang ,&nbsp;Shangbo Liu ,&nbsp;Haifeng Xu ,&nbsp;Simei Lin ,&nbsp;Zhexiu Yu ,&nbsp;Linyuan Li ,&nbsp;Huaguo Huang","doi":"10.1016/j.jag.2024.104285","DOIUrl":"10.1016/j.jag.2024.104285","url":null,"abstract":"<div><div>Leaf chlorophyll content (LCC) retrieval from remote sensing imagery is essential for monitoring vegetation growth and stress in the agroforestry industry. Many remote sensing inversion methods for estimating LCC primarily rely on 1D radiative transfer models (RTMs) that abstract canopies into horizontal layers or simple geometric primitives. Yet, this methodology faces challenges when applied to heterogeneous canopies, particularly in fine-scale mapping where each pixel's reflectance is significantly influenced by its surroundings, e.g. crown shadows. While 3D RTMs hold promise for addressing these challenges by explicitly describing complex canopy structures, their computational demands and the complexity involved in parameterizing detailed 3D structures limit the generation of extensive training datasets, requiring simulations across numerous parameter combinations. In this study, we used a semi-empirically accelerated 3D RTM, termed Semi-LESS, with a 1D residual network to accurately retrieve leaf chlorophyll content (LCC) from UAV images and LiDAR data at a 3-m resolution. We first reconstructed structures of forest plots using UAV LiDAR point cloud, based on which, UAV images with varying leaf and soil optical properties are simulated using the Semi-LESS. Subsequently, a training dataset consisting LCC and its corresponding reflectance was generated from the simulated UAV images by focusing on sunlit pixels. A 1D residual network is trained using the training dataset for LCC estimation. For comparison, we also trained an estimation model using a dataset generated from PROSAIL. The results show that estimation model trained with Semi-LESS surpasses PROSAIL in retrieving LCC from both simulation datasets and field measurements of two forest plots. The RMSE of Semi-LESS was 5.40–6.92 µg/cm² for simulation datasets and 8.21–9.76 µg/cm² for field measurements, whereas PROSAIL exhibited lower accuracy with an RMSE of 7.76–9.83 µg/cm² for simulation datasets and 12.76–13.06 µg/cm² in field measurements. The results demonstrate that Semi-LESS coupled with deep learning is reliable and has great potential for LCC mapping using UAV images, which is particularly useful for fine-scale applications such as crop and orchard monitoring. This approach also highlights the impact of shadows on LCC retrieval.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"135 ","pages":"Article 104285"},"PeriodicalIF":7.6,"publicationDate":"2024-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142721590","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"GNSS-denied geolocalization of UAVs using terrain-weighted constraint optimization","authors":"Fushan Yao,&nbsp;Chaozhen Lan,&nbsp;Longhao Wang,&nbsp;Hongfa Wan,&nbsp;Tian Gao,&nbsp;Zijun Wei","doi":"10.1016/j.jag.2024.104277","DOIUrl":"10.1016/j.jag.2024.104277","url":null,"abstract":"<div><div>Accurate geolocation using Global Navigation Satellite Systems (GNSS) is essential for safe and long-range unmanned aerial vehicles (UAVs) flights. However, GNSS systems are susceptible to blockages, jamming, and spoofing attacks. Localization using onboard cameras and satellite images provides a promising solution for UAVs operating in GNSS-denied environments. In this paper, we developed a novel UAV visual localization system for GNSS-denied situations, both day and night, that integrates image matching, visual odometry (VO), and terrain-weighted constraint optimization. First, an effective map management strategy is designed for satellite image chunking, real-time scheduling, and merging. Then, a 2D–3D geo-registration method, combining Bidirectional Homologous Points Search, is introduced to obtain accurate 3D virtual control points for UAV absolute localization. Lastly, a position estimation and optimization method, integrating the sliding window with terrain weighting constraints, is proposed to control position error accumulation and reduce position drift. Twenty experiments were conducted in typical and complex scenarios to validate our system’s resilience to altitude changes, trajectory variations, and rolling terrain. Our system demonstrated drift-free and viewpoint-robust, maintaining stability even in feature-poor environments and seasonal variations. It does not require loop closure, allowing for re-localization after positioning failures. Additionally, we utilized thermal infrared images to demonstrate the system’s performance in night-time conditions. With a Mean Absolute Error of less than 7 m, it can be a powerful complement to GNSS in the event of GNSS-Denied environments. All demonstration videos of our system can be found at <span><span>https://github.com/YFS90/GNSS-Denied-UAV-Geolocalization</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"135 ","pages":"Article 104277"},"PeriodicalIF":7.6,"publicationDate":"2024-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142704570","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Improved early detection of wheat stripe rust through integration pigments and pigment-related spectral indices quantified from UAV hyperspectral imagery","authors":"Anting Guo ,&nbsp;Wenjiang Huang ,&nbsp;Binxiang Qian ,&nbsp;Kun Wang ,&nbsp;Huanjun Liu ,&nbsp;Kehui Ren","doi":"10.1016/j.jag.2024.104281","DOIUrl":"10.1016/j.jag.2024.104281","url":null,"abstract":"<div><div>Wheat stripe rust is a significant disease affecting wheat growth, often referred to as the “cancer of wheat”. Early and accurate detection of stripe rust is crucial for enabling crop managers to implement effective control measures. Hyperspectral remote sensing methods for crop disease detection have gained significant attention. However, commonly used spectral bands or spectral indices (SIs) from hyperspectral data often fail to capture the subtle changes associated with the early stages of crop diseases accurately. In this study, we propose a method for early detection of wheat stripe rust by combining pigments and SIs retrieved from UAV hyperspectral imagery. We acquired hyperspectral images of wheat stripe rust at 7, 16, and 23 days post-inoculation (DPI) using a UHD 185 hyperspectral sensor (450–950 nm) mounted on an S1000 hexacopter UAV. Pigments, including chlorophylls (Cab), carotenoids (Car), anthocyanins, Cab/Car, and 11 pigment-related SIs, were extracted from UAV hyperspectral images using radiative transfer modeling. The early detection model for wheat stripe rust was developed using these parameters and machine learning algorithms. The results indicated selected pigments and SIs effectively distinguished stripe rust-infected wheat from healthy wheat at 7, 16, and 23 DPI. Models that combine pigments and SIs (PSIMs) perform better than those relying solely on SIs (SIMs) or pigments (PMs). Notably, the RF-based PSIM achieved overall accuracies of 78.1 % and 81.3 % during the asymptomatic (7 DPI) and minimally symptomatic (16 DPI) phases of disease, respectively. Additionally, the pigments in the PSIM contributed more significantly than the SIs, highlighting the importance of pigments in the early detection of stripe rust. Overall, the method combining pigments and spectral indices proposed in this study effectively enhances the early detection of wheat stripe rust and offers valuable insights into the early detection of other crop diseases.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"135 ","pages":"Article 104281"},"PeriodicalIF":7.6,"publicationDate":"2024-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142704538","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}