Statewide Forest Canopy Cover Mapping of Florida Using Synergistic Integration of Spaceborne LiDAR, SAR, and Optical Imagery

Remote Sensing, Год журнала: 2025, Номер 17(2), С. 320 - 320

Опубликована: Янв. 17, 2025

Southern U.S. forests are essential for carbon storage and timber production but increasingly impacted by natural disturbances, highlighting the need to understand their dynamics recovery. Canopy cover is a key indicator of forest health resilience. Advances in remote sensing, such as NASA’s GEDI spaceborne LiDAR, enable more precise mapping canopy cover. Although provides accurate data, its limited spatial coverage restricts large-scale assessments. To address this, we combined with Synthetic Aperture Radar (SAR), optical imagery (Sentinel-1 GRD Landsat–Sentinel Harmonized (HLS)) data create comprehensive map Florida. Using random algorithm, our model achieved an R2 0.69, RMSD 0.17, MD 0.001, based on out-of-bag samples internal validation. Geographic coordinates red spectral channel emerged most influential predictors. External validation airborne laser scanning (ALS) across three sites yielded 0.70, 0.29, −0.22, confirming model’s accuracy robustness unseen areas. Statewide analysis showed lower southern versus northern Florida, wetland exhibiting higher than upland sites. This study demonstrates potential integrating multiple sensing datasets produce vegetation maps, supporting management sustainability efforts

Язык: Английский

---

Using multi-platform LiDAR to guide the conservation of the world's largest temperate woodland

Remote Sensing of Environment, Год журнала: 2023, Номер 296, С. 113745 - 113745

Опубликована: Июль 31, 2023

Australia's Great Western Woodlands are the largest intact temperate woodland ecosystem on Earth, spanning an area size of average European country. These woodlands part one world's biodiversity hotspots and, despite subsisting just 200–400 mm rainfall a year, can store considerable amounts carbon. However, they face growing pressure from combination climate change and increasingly frequent large wildfires, which have burned over third these slow-growing, fire-sensitive in last 50 years alone. To develop conservation strategies that bolster long-term resilience this unique ecosystem, we urgently need to understand how much old-growth habitat remains where it is distributed across vast region. tackle challenge, brought together data extensive network field plots region combined with information vegetation 3D structure derived drone, airborne spaceborne LiDAR. Using dataset, developed novel modelling framework generate first high-resolution maps tree age entire We found 41.2% covered by stands, equivalent approximately 39,187 km2. Only 10% fall within current protected areas managed state government. Instead, most remaining either Ngadju Indigenous Protected Area (26.9%) or outside formal leaseholds privately owned lands (57.2%). Our will help guide targeted management Woodlands. Moreover, developing robust pipeline for integrating LiDAR multiple platforms, our study paves way mapping carbon storage open heterogeneous ecosystems space.

Язык: Английский

---

Forest Aboveground Biomass Estimation Using Multisource Remote Sensing Data and Deep Learning Algorithms: A Case Study over Hangzhou Area in China

Remote Sensing, Год журнала: 2024, Номер 16(6), С. 1074 - 1074

Опубликована: Март 19, 2024

The accurate estimation of forest aboveground biomass is great significance for management and carbon balance monitoring. Remote sensing instruments have been widely applied in parameters inversion with wide coverage high spatiotemporal resolution. In this paper, the capability different remote-sensed imagery was investigated, including multispectral images (GaoFen-6, Sentinel-2 Landsat-8) various SAR (Synthetic Aperture Radar) data (GaoFen-3, Sentinel-1, ALOS-2), estimation. particular, based on inventory Hangzhou China, Random Forest (RF), Convolutional Neural Network (CNN) Networks Long Short-Term Memory (CNN-LSTM) algorithms were deployed to construct models, respectively. estimate accuracies evaluated under configurations methods. results show that data, ALOS-2 has a higher accuracy than GaoFen-3 Sentinel-1. Moreover, GaoFen-6 slightly worse Landsat-8 optical contrast single source, integrating multisource can effectively enhance accuracy, improvements ranging from 5% 10%. CNN-LSTM generally performs better CNN RF, regardless used. combination provided best case achieve maximum R2 value up 0.74. It found majority values study area 2018 ranged 60 90 Mg/ha, an average 64.20 Mg/ha.

Язык: Английский

---

High-Resolution Canopy Height Mapping: Integrating NASA’s Global Ecosystem Dynamics Investigation (GEDI) with Multi-Source Remote Sensing Data

Remote Sensing, Год журнала: 2024, Номер 16(7), С. 1281 - 1281

Опубликована: Апрель 5, 2024

Accurate structural information about forests, including canopy heights and diameters, is crucial for quantifying tree volume, biomass, carbon stocks, enabling effective forest ecosystem management, particularly in response to changing environmental conditions. Since late 2018, NASA’s Global Ecosystem Dynamics Investigation (GEDI) mission has monitored global structure using a satellite Light Detection Ranging (LiDAR) instrument. While GEDI collected billions of LiDAR shots across near-global range (between 51.6°N >51.6°S), their spatial distribution remains dispersed, posing challenges achieving complete coverage. This study proposes evaluates an approach that generates high-resolution height maps by integrating data with Sentinel-1, Sentinel-2, topographical ancillary through three machine learning (ML) algorithms: random forests (RF), gradient boost (GB), classification regression trees (CART). To achieve this, the secondary aims included following: (1) assess performance ML algorithms, RF, GB, CART, predicting heights, (2) evaluate our reference from models (CHMs), (3) compare other two existing maps. RF GB were top-performing best 13.32% 16% root mean squared error broadleaf coniferous respectively. Validation proposed revealed 100th 98th percentile, followed average 75th, 90th, 95th, percentiles (AVG), most accurate metrics real heights. Comparisons between predicted CHMs demonstrated predictions stands (R-squared = 0.45, RMSE 29.16%).

Язык: Английский

---

Evaluating the performance of airborne and spaceborne lidar for mapping biomass in the United States' largest dry woodland ecosystem

Remote Sensing of Environment, Год журнала: 2024, Номер 308, С. 114196 - 114196

Опубликована: Май 16, 2024

Язык: Английский

---

Machine learning feature importance selection for predicting aboveground biomass in African savannah with landsat 8 and ALOS PALSAR data

Machine Learning with Applications, Год журнала: 2024, Номер 16, С. 100561 - 100561

Опубликована: Май 16, 2024

In remote sensing, multiple input bands are derived from various sensors covering different regions of the electromagnetic spectrum. Each spectral band plays a unique role in land use/land cover characterization. For example, while integrating for predicting aboveground biomass (AGB) is important achieving high accuracy, reducing dataset size by eliminating redundant and irrelevant features essential enhancing performance machine learning algorithms. This accelerates process, thereby developing simpler more efficient models. Our results indicate that compared individual sensor datasets, random forest (RF) classification approach using recursive feature elimination (RFE) increased accuracy based on F score 82.86% 26.19 respectively. The mutual information regression (MIR) method shows slight increase when considering but its decreases all taken into account Overall, combination Landsat 8, ALOS PALSAR backscatter, elevation data selected RFE provided best AGB estimation RF XGBoost contrast to k-nearest neighbors (KNN) support vector machines (SVM), no significant improvement was detected even MIR were used. effect parameter optimization found be than other methods. maps show patterns estimates consistent with those reference dataset. study how prediction errors can minimized selection ML classifiers.

Язык: Английский

---

Forest Emissions Reduction Assessment Using Optical Satellite Imagery and Space LiDAR Fusion for Carbon Stock Estimation

Remote Sensing, Год журнала: 2023, Номер 15(5), С. 1410 - 1410

Опубликована: Март 2, 2023

Forests offer significant climate mitigation benefits, but existing emissions reduction assessment methodologies in forest-based activities are not scalable, which limits the development of carbon offset markets. In this study, we propose a measurement method using optical satellite imagery and space LiDAR data fusion to assess forest reduction. Compared with ALS-based stock density estimation method, our approach presented strong scalability for mapping 10 m-resolution at large scale. It was observed that dense canopy top height estimated by combining GEDI Sentinel-2 could accurately predict measurements (R2 = 0.72). By conducting an on-site experiment ongoing project China, found consistency between assessed (589,169 tCO2e) official ex post-monitored monitoring report (598,442 tCO2e). Our results demonstrated carton is efficient economical assessment. The acquisition more over areas high frequencies space-based technology. We further discussed challenge building near-real-time system utilizing pointed out quality control framework should be established help us understand sources uncertainty LiDAR-based models improve from individual trees projects meet requirements standards better.

Язык: Английский

---

Accuracy Assessment of Gedi Terrain Elevation, Canopy Height, and Aboveground Biomass Density Estimates in Japanese Artificial Forests

Опубликована: Янв. 1, 2024

Global forests face severe challenges owing to climate change, making dynamic and accurate monitoring of forest conditions critically important. Forests in Japan, covering approximately 70% the country's land area, play a vital role yet often overlooked global forestry. Japanese are unique, with 50% comprising artificial forests, predominantly coniferous forests. Despite government's extensive use airborne Light Detecting Ranging (LiDAR) assess conditions, these data need more availability frequency. The Ecosystem Dynamics Investigation (GEDI), first Spaceborne LiDAR explicitly designed for vegetation monitoring, is expected provide significant value high-frequency high-accuracy monitoring. To accuracy GEDI we gathered reference from 53,967,770 trees via Aichi Prefecture, Japan. This was then compared corresponding GEDI-derived terrain elevations, canopy heights (GEDI RH98), aboveground biomass density (AGBD) estimates January 2019 November 2023. research also explored how different factors influence elevation estimates, including type beam, time acquisition (day or night), beam sensitivity, slope. Additionally, investigated effects various structural parameters, such as height-to-diameter ratio, crown length number on height AGBD. Our results showed that demonstrates high across slope rRMSE ranging 2.28% 3.25%. After geolocation adjustment, comparison derived demonstrated accuracy, exhibiting an 22.04%. In contrast, AGBD product lower 52.79%. findings indicated RH98 significantly influenced by whereas mainly impacted ratio. study provided baseline validation elevation, RH98, Furthermore, this provides valuable insights into precision metrics examining potential factors.

Язык: Английский

---

Mapping aboveground biomass in Indonesian lowland forests using GEDI and hierarchical models

Remote Sensing of Environment, Год журнала: 2024, Номер 313, С. 114384 - 114384

Опубликована: Авг. 24, 2024

Язык: Английский

---

Evaluating GEDI data fusions for continuous characterizations of forest wildlife habitat

Frontiers in Remote Sensing, Год журнала: 2023, Номер 4

Опубликована: Июнь 20, 2023

Continuous characterizations of forest structure are critical for modeling wildlife habitat as well assessing trade-offs with additional ecosystem services. To overcome the spatial and temporal limitations airborne lidar data studying wide-ranging animals monitoring through time, novel sampling sources, including space-borne Global Ecosystem Dynamics Investigation (GEDI) instrument, may be incorporated within fusion frameworks to scale up satellite-based estimates across continuous extents. The objectives this study were to: 1) investigate value satellite sources generating GEDI-fusion models 30 m resolution predictive maps eight measures six western U.S. states (Colorado, Wyoming, Idaho, Oregon, Washington, Montana); 2) evaluate suitability GEDI a reference source assess any spatiotemporal biases using samples data; 3) examine differences in products inclusion three keystone woodpecker species varying needs. We focused on two models, one that combined Landsat, Sentinel-1 Synthetic Aperture Radar, disturbance, topographic, bioclimatic predictor information (combined model), was restricted predictors (Landsat/topo/bio model). Model performance varied although all representing moderate high (model testing R 2 values ranging from 0.36 0.76). Results similar between map validations years model creation (2019–2020) hindcasted (2016–2018). Within our case studies, encounter rates inputs yielded AUC 0.76–0.87 observed relationships followed ecological understanding species. While results show promise use remote sensing fusions scaling metrics other applications broad extents, further assessments needed test their conservation interest biodiversity assessments.

Язык: Английский

---