Multispectral Satellite Imagery Research Articles

Detecting Pest-Infested Forest Damage through Multispectral Satellite Imagery and Improved UNet+.

Plant pests are the primary biological threats to agricultural and forestry production as well as forest ecosystem. Monitoring forest-pest damage via satellite images is crucial for the development of prevention and control strategies. Previous studies utilizing deep learning to monitor pest-infested damage in satellite imagery adopted RGB images, while multispectral imagery and vegetation indices were not used. Multispectral images and vegetation indices contain a wealth of useful information for detecting plant health, which can improve the precision of pest damage detection. The aim of the study is to further improve forest-pest infestation area segmentation by combining multispectral, vegetation indices and RGB information into deep learning. We also propose a new image segmentation method based on UNet++ with attention mechanism module for detecting forest damage induced by bark beetle and aspen leaf miner in Sentinel-2 images. The ResNeSt101 is used as the feature extraction backbone, and the attention mechanism scSE module is introduced in the decoding phase for improving the image segmentation results. We used Sentinel-2 imagery to produce a dataset based on forest health damage data gathered by the Ministry of Forests, Lands, Natural Resource Operations and Rural Development (FLNRORD) in British Columbia (BC), Canada, during aerial overview surveys (AOS) in 2020. The dataset contains the 11 original Sentinel-2 bands and 13 vegetation indices. The experimental results confirmed that the significance of vegetation indices and multispectral data in enhancing the segmentation effect. The results demonstrated that the proposed method exhibits better segmentation quality and more accurate quantitative indices with overall accuracy of 85.11%, in comparison with the state-of-the-art pest area segmentation methods.

Deep learning models for river classification at sub-meter resolutions from multispectral and panchromatic commercial satellite imagery

Remote sensing of the Earth’s surface water is critical in a wide range of environmental studies, from evaluating the societal impacts of seasonal droughts and floods to the large-scale implications of climate change. Consequently, a large literature exists on the classification of water from satellite imagery. Yet, previous methods have been limited by (1) the >10 m spatial resolution of public satellite imagery, (2) classification schemes that operate at the pixel level, and (3) the need for multiple spectral bands. We advance the state-of-the-art by (1) using commercial satellite imagery with panchromatic and multispectral resolutions of ∼ 30 cm and ∼ 1.2 m, respectively, (2) developing multiple fully convolutional neural networks (FCN) that can learn the morphological features of water bodies in addition to their spectral properties, and (3) FCN that can classify water even from panchromatic imagery. This study focuses on rivers in the Arctic, using images from the Quickbird-2, WorldView-1, WorldView-2, WorldView-3, and GeoEye satellites. Because no training data are available at such high resolutions, we construct those manually. First, we use the red, green, blue, and near-infrared bands of the 8-band multispectral sensors. Those trained models all achieve excellent precision and recall over 90% on validation data, aided by on-the-fly preprocessing of the training data specific to satellite imagery. In a novel approach, we then use results from the multispectral model to generate training data for FCN that only require panchromatic imagery, of which considerably more is available. Despite the smaller feature space, these models still achieve a precision and recall of over 85%. We provide our open-source codes and trained model parameters to the remote sensing community, which paves the way to a wide range of environmental hydrology applications at vastly superior accuracies and 1–2 orders of magnitude higher spatial resolution than previously possible.

Investigation of Alteration Deposit Zones of Porphyry Copper Ore Using Multispectral Satellite Imagery (Aster, Landsat-8 and Sentinel-2) and Ground Controls (Case study: MasjedDaghi copper deposit - NW Iran)

طراحی الگوریتم‌های سنجش از دور و توسعة روش‌های گوناگون پردازش تصاویر ماهواره‌ای، برای شناسایی کانسارهای مس پورفیری، ازجمله موضوعات مهم مطالعات در زمینة ارزیابی منابع معدنی و بهره‌برداری بهینه از آنهاست. به این منظور، تعیین نواحی دگرسانی ابزار مناسبی به‌منظور طراحی الگوهای مورد ‌قبول اکتشافی فراهم می‌آورد. در این پژوهش، با راهبردی جامع و با استفاده از تعیین حدود دگرسانی‌های مرتبط با کانسار مس پورفیری برمبنای مدل لوول و گیلبرت با سه نوع راهبرد متفاوت (پردازش‌های بصری، طیفی و آماری) و همچنین استخراج خط‌واره‌ها در منطقة مورد مطالعه، محدودة تمرکز مادة معدنی برای حفاری پیشنهاد شد. منطقة مورد مطالعه، در این مقاله، کانسار مس پورفیری مسجدداغی در شمال‌شرق استان آذربایجان‌شرقی است. در این پژوهش، از تصاویر ماهواره‌ای چندطیفی استر، سنجندة OLI لندست‌ـ 8 و سنتینل‌ـ 2 برای پردازش‌های گوناگون مانند ترکیبات نسبت‌های باندی، تحلیل مؤلفة اصلی و روش‌های پردازش طیفی پیکسل‌مبنا و زیرپیکسلی، ازجمله SAM و MTMF و پردازش‌های آماری مبتنی‌بر الگوریتم عملگر منطقی استفاده شد. در نهایت، با فازی‌سازی و تلفیق لایه‌های حاصل از پردازش‌های تصاویر ماهواره‌ای با ساختارهای هندسی منطقه (خط‌واره‌ها) که روی داده‌های سنتینل‌ـ 2 به دو روش خودکار و نیمه‌خودکار استخراج شدند، نتایج در فضای GIS تحلیل شد و پس از مقایسة نتایج ارائه‌شده با تحلیل نمونه‌های زمینی، صحت و تطابق مناطق مورد نظر تأیید شد. دقت کاربر و سازنده درمورد محدودة دارای اولویت به‌ترتیب 54/78% و 36/78% به‌دست آمد که معیار سنجش مناسب‌تری برای معرفی محدودة مرکز حفاری است.

China’s larch stock volume estimation using Sentinel-2 and LiDAR data

ABSTRACT Forest Stock Volume (FSV) is one of the key indicators in forestry resource investigation and management on local, regional, and national scales. Limited by the saturation problems of optical satellite remote-sensing imagery in the retrieving of stock volume, and the high cost of Light Detection And Ranging (LiDAR) data, it is still challenging to estimate FSV in a large area using single-sensor remote-sensing data. In this paper, a method integrated multispectral satellite imagery and LiDAR data was developed to map stock volume in a large area. A random forest model was adopted to estimate the stock volume of larch forest in China based on the training samples from the Airborne Laser Scanning (ALS)-derived stock volume and corresponding Sentinel-2 imagery. Validation using National Forest Inventory (NFI) data, ALS-derived stock volume and ground investigation data demonstrated that the estimated stock volume had a high accuracy (R2 = 0.59, RMSE = 59.69 m3/ha, MD = 39.96 m3/ha when validated with NFI data; R2 ranged from 0.77 to 0.85, RMSE ranged from 38.68 m3/ha to 67.38 m3/ha, MD ranged from 24.90 m3/ha to 37.27 m3/ha when validated with ALS stock volume; R2 = 0.42, RMSE = 79.10 m3/ha, MD = 62.06 m3/ha when validated with field investigation data). Results of this paper indicated the applicability of estimating stock volume of larch forest in a large area by combining Sentinel-2 data and airborne LiDAR data.

Seagrass mapping using high resolution multispectral satellite imagery: A comparison of water column correction models

Satellite remote sensing is an efficient and economical technique for studying coastal bottoms in clear and shallow waters. Accordingly, the main objective of this study is the generation of benthic maps using high spatial resolution multispectral images from the WorldView-2/3 satellites. In this context, one of the main challenges consists of eliminating the disturbances caused in the signal by the atmosphere, the sea surface, and the water column. Regarding the water column correction, there is controversy about its effectiveness to improve the results achieved. To assess the impact of the water column correction in seagrass mapping, two coastal areas with different characteristics have been selected. Specifically, an analysis has been carried out consisting of the assessment of the Lyzenga and Sagawa water column correction models to identify the algorithm that provides the best mapping precision and, additionally, to seek if this pre-processing stage is helpful when classifying the seabed. The classification models selected for the study were: Gaussian Naïve Bayes (GNB), Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Subspace KNN (S-KNN). Machine learning techniques have proven to achieve better results and, in particular, SVM and KNN models provide the best overall accuracy. The results after benthic mapping have demonstrated, that image classification without water column corrections provides better accuracy (95.36% and 99.20%) than using Lyzenga (73.49% and 97.80%) or Sagawa (82.04% and 99.10%), for Case 2 and 1 waters, respectively.

A machine learning approach to mapping canopy gaps in an indigenous tropical submontane forest using WorldView-3 multispectral satellite imagery

SummarySelective logging in tropical forests may lead to deforestation and forest degradation, so accurate mapping of it will assist in forest restoration, among other ecological applications. This study aimed to track canopy tree loss due to illegal logging of the important hardwood tree Ocotea usambarensis in a closed-canopy submontane tropical forest by evaluating the mapping potential of the very-high-resolution WorldView-3 multispectral dataset using random forest (RF) and support vector machine (SVM) with radial basis function kernel classifiers. The results show average overall accuracies of 92.3 ± 2.6% and 94.0 ± 2.1% for the RF and SVM models, respectively. Average kappa coefficients were 0.88 ± 0.03 for RF and 0.90 ± 0.02 for SVM. The user’s and producer’s accuracies for both classifiers were in the range of 84–100%. This study further indicates that vegetation indices derived from bands 5 and 6 helped detect canopy gaps in the study area. Both variable importance measurement in the RF algorithm and pairwise feature selection proved useful in identifying the most pertinent variables in the classification of canopy gaps. These findings could allow forest managers to improve methods of detecting canopy gaps at larger scales using remote sensing data and relatively little additional fieldwork.

Mapping tree species proportions from satellite imagery using spectral–spatial deep learning

Remote sensing can be used to collect information related to forest management. Previous studies demonstrated the potential of using multispectral satellite imagery for classifying tree species. However, methods that can map tree species in mixed forest stands on a large scale are lacking. We propose an innovative method for mapping the proportions of tree species using Sentinel-2 imagery. A convolutional neural network was used to quantify the per-pixel basal area proportions of tree species considering the neighbouring environment (spectral–spatial deep learning). A nested U-shaped neural network (UNet++) architecture was implemented. We produced a map of the entire Wallonia Region (southern Belgium). Nine species or groups of species were considered: Spruce genus, Oak genus, Beech, Douglas fir, Pine genus, Poplar genus, Larch genus, Birch genus, and remaining species. The training dataset for the convolutional neural network model was prepared using a map of forest parcels extracted from the public forest administration’s geodatabase of Wallonia. The accuracy of the predicted map covering the region was independently assessed using data from the regional forest inventory of Wallonia. A robust assessment method for tree species proportions maps was proposed for assessing the (1) majority species, (2) species composition (presence or absence), and (3) species proportions (proportion values). The achieved value of indicator OAmaj (0.73) shows that our approach can map the majority tree species in mixed and pure forest stands. Indicators MS (0.89), MPS (0.72) and MUS (0.83) support that the model can predict the species composition in most cases in the study area. Spruce genus, Oak genus, Beech, and Douglas fir achieved the best results, with PAs and UAs close to or higher than 0.70. Particularly, high performance was achieved for detecting Oak genus and Beech in low area proportions: PAs and UAs higher than 0.70 from the 0.4 proportion. Predicted proportions had a Radj2 of 0.50. The proposed method, which uses spectral–spatial deep learning to map the proportions of tree species, is innovative because it was adapted to the complexity of mixed forests and spatial resolution of current satellite imagery. Additionally, it optimises the use of available forest data in the model conception by considering all pixels from pure stands to highly mixed forest stands. When forest inventories are available in a broad sense, that is, georeferenced areas with the proportions of tree species, this method is highly reproducible and applicable at a large scale, offering potential for use in forest management.

Detecting Vegetation to Open Water Transitions in a Subtropical Wetland Landscape from Historical Panchromatic Aerial Photography and Multispectral Satellite Imagery

Over the last century, direct human modification has been a major driver of coastal wetland degradation, resulting in widespread losses of wetland vegetation and a transition to open water. High-resolution satellite imagery is widely available for monitoring changes in present-day wetlands; however, understanding the rates of wetland vegetation loss over the last century depends on the use of historical panchromatic aerial photographs. In this study, we compared manual image thresholding and an automated machine learning (ML) method in detecting wetland vegetation and open water from historical panchromatic photographs in the Florida Everglades, a subtropical wetland landscape. We compared the same classes delineated in the historical photographs to 2012 multispectral satellite imagery and assessed the accuracy of detecting vegetation loss over a 72 year timescale (1940 to 2012) for a range of minimum mapping units (MMUs). Overall, classification accuracies were >95% across the historical photographs and satellite imagery, regardless of the classification method and MMUs. We detected a 2.3–2.7 ha increase in open water pixels across all change maps (overall accuracies > 95%). Our analysis demonstrated that ML classification methods can be used to delineate wetland vegetation from open water in low-quality, panchromatic aerial photographs and that a combination of images with different resolutions is compatible with change detection. The study also highlights how evaluating a range of MMUs can identify the effect of scale on detection accuracy and change class estimates as well as in determining the most relevant scale of analysis for the process of interest.

2D/3D SOIL CONSUMPTION TRACKING IN A MARBLE QUARRY DISTRICT

Abstract. Complex extractive districts, such as the marble quarries in the Apuan Alps (northern Italy), require soil consumption monitoring over the years that could be achieved through high-resolution remotely sensed data. To derive 2D and 3D indicators with appropriate resolution for annual monitoring of high-resolution changes in soil consumption, aerial images, LiDAR acquisitions, satellite data, and Remotely Piloted Aircraft Systems (RPAS) acquisitions were used. In particular, open-access Sentinel-2 multispectral satellite imagery with a spatial resolution of 10 m was used to assess cover changes (2D), and then refined by manual interpretation for 5 years (2016-2021). 3D changes were detected by comparing free aerial LiDAR data from 2009 and 2017, integrated with two stereo models obtained from Pléiades high-resolution satellite images from 2020 and 2022. 3D changes observed over the years by algebraic elevation comparison, performed in QGIS 3.x environment, highlight quarries characterized by intense mining activities (extracted marble blocks, characterized by positive elevation differences) and quarry area management (debris disposal and service infrastructure construction, characterized by negative elevation differences). The combined use of 2D and 3D change indicators can be challenging in order to correctly represent soil consumption over the years. A dual 2D/3D webgis client have been developed for proper representation of 2D/3D spatial indicators of ongoing extraction activities in the Carrara marble basin: high-resolution images have been served as tiled data, while 2D/3D spatial indicators are served as static and/or tiled vector data. Open-Source libraries have used in data processing, serving and representation inside a map interface.

Using deep convolutional neural networks to forecast spatial patterns of Amazonian deforestation

Abstract Tropical forests are subject to diverse deforestation pressures while their conservation is essential to achieve global climate goals. Predicting the location of deforestation is challenging due to the complexity of the natural and human systems involved but accurate and timely forecasts could enable effective planning and on‐the‐ground enforcement practices to curb deforestation rates. New computer vision technologies based on deep learning can be applied to the increasing volume of Earth observation data to generate novel insights and make predictions with unprecedented accuracy. Here, we demonstrate the ability of deep convolutional neural networks (CNNs) to learn spatiotemporal patterns of deforestation from a limited set of freely available global data layers, including multispectral satellite imagery, the Hansen maps of annual forest change (2001–2020) and the ALOS PALSAR digital surface model, to forecast deforestation (2021). We designed four model architectures, based on 2D CNNs, 3D CNNs, and Convolutional Long Short‐Term Memory (ConvLSTM) Recurrent Neural Networks (RNNs), to produce spatial maps that indicate the risk to each forested pixel (~30 m) in the landscape of becoming deforested within the next year. They were trained and tested on data from two ~80,000 km2 tropical forest regions in the Southern Peruvian Amazon. The networks could predict the location of future forest loss to a high degree of accuracy (F1 = 0.58–0.71). Our best performing model (3D CNN) had the highest pixel‐wise accuracy (F1 = 0.71) when validated on 2020 forest loss (2014–2019 training). Visual interpretation of the mapped forecasts indicated that the network could automatically discern the drivers of forest loss from the input data. For example, pixels around new access routes (e.g. roads) were assigned high risk, whereas this was not the case for recent, concentrated natural loss events (e.g. remote landslides). Convolutional neural networks can harness limited time‐series data to predict near‐future deforestation patterns, an important step in harnessing the growing volume of satellite remote sensing data to curb global deforestation. The modelling framework can be readily applied to any tropical forest location and used by governments and conservation organisations to prevent deforestation and plan protected areas.

Classification of Alpine Grasslands in Cold and High Altitudes Based on Multispectral Landsat-8 Images: A Case Study in Sanjiangyuan National Park, China

Land-use–cover change (LUCC)/vegetation cover plays a critical role in Earth system science and is a reflection of human activities and environmental changes. LUCC will affect the structure and function of ecosystems and a series of other terrestrial surface processes, such as energy exchange, water circulation, biogeochemical circulation, and vegetation productivity. Therefore, accurate LUCC mapping and vegetation cover monitoring are the bases for simulating the global carbon and hydrological cycles, studying the interactions of the land surface and climate, and assessing land degradation. Based on field GPS surveys and UAV data, with cloud-free and snow/glacier algorithms and the SVM classifier to train and model alpine grassland, the alpine grassland and LUCC were extracted by using Landsat-8 OLI satellite images in Sanjiangyuan National Park in this paper. The latest datasets of vegetation types with 30 m × 30 m spatial resolution in the three parks were prepared and formed. The classification results show that the SVM classifier could better distinguish the major land-use types, and the overall classification accuracy was very high. However, in the alpine grassland subcategories, the classification accuracies of the four typical grasslands were relatively low, especially between desert steppes and alpine meadows, and desert steppes and alpine steppes. It manifests the limitations of Landsat-8 multispectral remote sensing imageries in finer-resolution grassland classifications of high-altitude alpine mountains. The method can be utilized for other multispectral satellite imageries with the same band matching, such as Landsat 7, Landsat 9, Sentinel-2, etc. The method described in this paper can rapidly and efficiently process annual alpine grassland maps of the source areas of the Yellow River, the Yangtze River, and the Lancang River. It can provide timely and high-spatial-resolution datasets for supporting scientific decisions for the sustainable management of Sanjiangyuan National Park.

Field-scale estimation of sugarcane leaf nitrogen content using vegetation indices and spectral bands of Sentinel-2: Application of random forest and support vector regression

Nitrogen is an essential factor for assessing the quality of sugarcane during the growing season, as deficiency of this component significantly reduces crop yield . The Kjeldahl method is the most common approach to measuring sugarcane nitrogen, but it is a laborious, costly, and time-consuming process. Conversely, multispectral satellite imagery can provide timely, cost-effective, and large-scale information on the nitrogen content in sugarcane fields. The current study applied random forest (RF) and support vector regression (SVR) models to estimate sugarcane leaf nitrogen using vegetation indices and spectral bands of Sentinel-2. In-situ data was taken from 45 farms (1125 ha) in a sugarcane production agro-industrial complex in southwest Iran. The global environmental monitoringindex (GEMI), chlorophyllindexgreen (Clgreen), and Sentinel-2 red-edge position index (S2REP) were found to be the most important variables related to sugarcane nitrogen. The coefficient of determination (R2) for RF and SVR was 0.59 and 0.58, respectively, and the corresponding root mean square error (RMSE) was 0.08 and 0.09, respectively. Despite the similar performances of the two models, RF showed higher accuracy; however, to improve the results, the use of multi-temporal data for model calibration is recommended.

Environmental impact assessment of limestone quarry using multispectral satellite imagery

Environmental impact assessment of limestone quarry using multispectral satellite imagery

Mapping, Inventory and Change Detection of Wetlands of Thavanur Grama Panchayath using Multispectral Satellite Imagery

Wetlands are the submerged or waters saturated lands, both natural and man-made, permanent or temporary, with water that is static or flowing, fresh, brackish or salt, including areas of marine water, the depth of which at low tide does not exceed 6 meters. Effective wetlands management and protection are critical. Accurate and comprehensive wetland classification maps as well as spatiotemporal change information are essential for ecological protection and local government decisions. Wetland mapping and classification help to preserve and improve wetland quality.
 A study was conducted on wetland mapping, inventory and change detection wetlands of Thavanur Grama Panchayath in Malappuram district of Kerala using multispectral satellite imageries of high resolution (2.4x2.4m) during the year 2020-2021. The image processing was carried out by Visual Interpretation Technique. The accuracy of mapping was assessed by kappa coefficient.
 The various wetland classes found in Thavanur Grama Panchayath were Aquaculture, Marshy land, River and other ponds and small waterbodies. The major wetlands identified in the Panchayath were Ayankalam kayal, Maravanchery kaayal, Varo kaayal, Thavanur kaayal (marshy type wetlands), Bharathapuzha River, Ayankalam aquaculture, Mathur aquaculture and several other ponds. The change detection analysis showed that the percentage change in wetland during the decade was found maximum for pond and well (-33.18%). The major land use changes during the period 2008 and 2018 were that coconut plantation increased by 70.79 ha, paddy land decreased by 61.62 ha and marshy land decreased by 7.04 ha. The kappa coefficient of mapping was obtained as 0.93 which indicted good accuracy.

Detection and mapping of May 2021 flood in Beaufort, Sabah using Sentinel-1 SAR and Sentinel-2 multispectral in Google Earth Engine

Recurring floods severely impacted the livelihood and socio-economic. It causes disruption of clean water, electricity, communications, properties damages and sometimes loss of life. Information on flooded areas is crucial for effective emergency responses support. In this study we used Sentinel 1 (S-1) C-band and Sentinel 2 (S-2) Multispectral satellite imageries where wider area covered in 12 days repeat satellite pass. The flood event on the 26 May 2021 was identified and we retrieved the S-1 GRD SAR imagery and S-2 level-2A BOA in GEE environment. We analysed the S-1 VV, VH, VV/VH imagery by pixels clustering using object based SNIC classification and Machine Learning (ML) algorithm for extraction of waterbody. Meanwhile for the S-2 we used MNDWI and extracted the waterbody area using thresholding value. We obtained the final flooded area of S-1 and S-2 by subtraction with permanent waterbody. The S-2 flood estimation results were better than S-1. However, S-2 limited to cloud free and less cloudy coverage while S-1 lacking of ability to identify flood in detailed was influenced by slope shadow area. This study provides the basis of detection and mapping floods using S-1 and S-2 imageries through Machine Learning techniques in GEE for local scope of Sabah, Borneo region and Malaysia.

Determination of Coastline Changes by Using Geospatial Technology Along the Pantai Kuala Nerus, Terengganu

The phenomenon of coastal erosion is a natural disaster that often occurs every year on the East Coast of Peninsular Malaysia. Coastal erosion can be identified through changes in coastlines found in coastal areas. Beaches in the state of Terengganu often face the problem of big waves and strong winds during the monsoon season. Coastal erosion can be identified through changes in coastlines found in coastal areas. The Ruin Monsoon phenomenon which causes tides and violent waves as high as almost four meters has eroded the land little by little over the past few decades. This study aims to determine the coastline change from 2016 until 2020 by using geospatial technology at Pantai Kuala Nerus, Terengganu. Furthermore, this study has three objectives to achieve. The first objective is to identify the coastline by using multispectral satellite imagery. The second objective is to analyze the rate of erosion and accretion along Pantai Kuala Nerus. The third objective is to determine the category of Pantai Kuala Nerus coastline according to the Malaysia National Coast Erosion Study (NCES) guidelines. The study concludes almost all erosion area in Pantai Kuala Nerus is included in critical and high erosion rate.

Multispectral satellite imagery processing to recognize and analyze archaeological sites in the central area of Sicily (Italy)

This article aims to improve the study of archaeological sites in the territory of Milena, a town located in Sicily (Italy). Between the 80 s and 90 s different excavation campaigns had documented numerous prehistoric sites. However, most of the ancient settlements have yet to be discovered and studied. The search operations are made difficult by the large size of the territory and its geomophorological characteristics. In fact, many settlements stand on chalky hills that are rapidly crumbling, risking damage to the archaeological remains. To intervene as soon as possible, we have relied on the use of modern approaches, capable of speeding up the work of researchers. Here we propose a new approach based on remote sensing and the GIS technology to detect archaeological sites. In particular, we used multispectral remote sensing data in a GIS environmental both for predictive and post-dictive analyses. We were able to locate areas where there are ceramics and elements that can be recoded to human settlements. The quality of the results depends on the choice of the remotely sensed images, which can have different spectral characteristics, on the acquisition period, but also on the preprocessing algorithms adopted for the classification in the GIS environment.

Spaceborne LiDAR and animal-environment relationships: An assessment for forest carnivores and their prey in the Greater Yellowstone Ecosystem

Animal conservation requires understanding animal-habitat relationships. The integration of novel remote sensing platforms such as Light Detection and Ranging (LiDAR) technology has dramatically improved the resolution of insight when evaluating animal-habitat relationships by characterizing forest structure. However, conventional LiDAR collection (e.g., airborne or terrestrial laser scanning) may be limited by small spatial extents and logistical constraints (e.g., budget) associated with sampling. NASA’s Global Ecosystem Dynamics Investigation (GEDI) mission provides an alternative and complement to conventional LiDAR sampling with globally available waveform LiDAR, which is being collected to characterize vertical and horizontal structure of Earth’s forests. Forest carnivores are wide-ranging species occupying forested ecosystems, and are generally associated with vertical and horizontal forest structure for their survival and reproduction. We evaluated patterns in occurrence and habitat use of forest carnivores, which included Pacific martens (Martes caurina), Rocky Mountain red foxes (Vulpes vulpes macroura), and coyotes (Canis latrans) and patterns in occurrence of their prey; American red squirrels (Tamiasciurus hudsonicus) and snowshoe hares (Lepus americanus). Camera trap data were collected during the 2014–2017 winters in the Greater Yellowstone Ecosystem in Wyoming, USA. Our objectives were to (1) combine GEDI samples with multispectral satellite imagery from Landsat 8 to upscale vertical forest structure metrics; (2) assess the relative importance of environmental characteristics influencing occurrence and habitat use of forest-associated predators and prey; and (3) determine if GEDI-derived variables aided our efforts in characterizing animal-environment relationships. We used Random Forest regression models to upscale GEDI samples across our study area and implemented a multi-tiered approach using generalized linear mixed effect models to simultaneously evaluate animal-environment relationships and how GEDI-derived metrics improved the animal-habitat models. GEDI-derived metrics of relative height and foliage height diversity improved our animal-environment models and were among the strongest covariates (effect sizes were 1.3–1.8 times larger than the next closest) in the coyote, red squirrel, and snowshoe hare models. All five species were influenced to some degree by the frequency of rebaiting a camera trap and varying conditions of snow depth. Collectively, our work indicates forest canopy height and complexity variables significantly improved our ability to assess the importance of forest characteristics on forest carnivores and their prey. Indeed, there is an untapped opportunity to enhance animal ecology and conservation planning with continued integration of GEDI information with freely available satellite data to characterize attributes of forest structure across expansive areas.

Multi-sensor and multi-platform consistency and interoperability between UAV, Planet CubeSat, Sentinel-2, and Landsat reflectance data

ABSTRACT Unmanned aerial vehicle (UAV) and satellite data have considerable complementarity for platform inter-operability, data fusion studies, calibration and validation efforts, and various multiscale analyses. To optimize cross-platform synergies between field-deployable UAV and space-based satellite systems, an understanding of spectral characteristics and compatibility is required. Here, we present the assessment of spectral consistency, undertaking a pixel-to-pixel similarity assessment of co-registered reflectance maps using corresponding spectral bands from UAV and satellite multispectral imagery. A high-resolution centimeter-scale UAV-mounted MicaSense RedEdge-MX sensor is intercompared against variable-resolution multi-spectral sensors on-board PlanetScope, Sentinel-2 and Landsat 8 platforms. Sampling from within an urban environment that covers a range of both natural and man-made surfaces, we employ ground-based spectroradiometer data to evaluate pixel-level responses, using regression analysis and measurements of relative root mean square error (rRMSE) to assess for factors such as spatial and spectral misalignment. Using two radiometric correction approaches for the UAV data, we found that a vicarious radiometric correction was more accurate than a linear empirical line method, with the former improving rRMSE by between 1.6% and 20.11% when assessed against spectroradiometer measurements. Spectral band misalignment between the UAV and satellite sensors affected their spectral consistency, causing different reflectance values for the same object in the corresponding UAV and satellite bands, with the issue amplified over specific land-cover classes (e.g. grass in the red edge part of the spectrum). Using the standard deviation of a UAV-derived normalized difference vegetation index (NDVI) as a metric of spatial heterogeneity, larger differences between the UAV and satellite-based NDVI were observed for different ground features in response to both land-cover boundary and shadow effects. Interestingly, higher spatial heterogeneity did not necessarily lead to higher spectral inconsistencies. It was also determined that as spatial scale differences between the UAV and satellite platforms increased, the lower was the impact of geometric misregistration on their consistency. Indeed, the rRMSE between the reflectance values of the UAV-based spectral bands and the corresponding satellite imagery was smaller at lower resolution (e.g. Landsat 8) than higher resolution (e.g. PlanetScope). Overall, the study provides insight into the collective effect of spectral and spatial misalignments on the degree of spectral consistency that can be expected between UAV and satellite data, guiding robust radiometric intercalibration efforts and the potential for improved synergy and interoperability between UAV and satellite data.

Machine-Learning for Mapping and Monitoring Shallow Coral Reef Habitats

Mapping and monitoring coral reef benthic composition using remotely sensed imagery provides a large-scale inference of spatial and temporal dynamics. These maps have become essential components in marine science and management, with their utility being dependent upon accuracy, scale, and repeatability. One of the primary factors that affects the utility of a coral reef benthic composition map is the choice of the machine-learning algorithm used to classify the coral reef benthic classes. Current machine-learning algorithms used to map coral reef benthic composition and detect changes over time achieve moderate to high overall accuracies yet have not demonstrated spatio-temporal generalisation. The inability to generalise limits their scalability to only those reefs where in situ reference data samples are present. This limitation is becoming more pronounced given the rapid increase in the availability of high temporal (daily) and high spatial resolution (<5 m) multispectral satellite imagery. Therefore, there is presently a need to identify algorithms capable of spatio-temporal generalisation in order to increase the scalability of coral reef benthic composition mapping and change detection. This review focuses on the most commonly used machine-learning algorithms applied to map coral reef benthic composition and detect benthic changes over time using multispectral satellite imagery. The review then introduces convolutional neural networks that have recently demonstrated an ability to spatially and temporally generalise in relation to coral reef benthic mapping; and recurrent neural networks that have demonstrated spatio-temporal generalisation in the field of land cover change detection. A clear conclusion of this review is that existing convolutional neural network and recurrent neural network frameworks hold the most potential in relation to increasing the spatio-temporal scalability of coral reef benthic composition mapping and change detection due to their ability to spatially and temporally generalise.