Integration of machine learning and remote sensing for above ground biomass estimation through Landsat-9 and field data in temperate forests of the Himalayan region

Ecological Informatics, Год журнала: 2024, Номер 82, С. 102732 - 102732

Опубликована: Июль 22, 2024

Accurately estimating aboveground biomass (AGB) in forest ecosystems facilitates efficient resource management, carbon accounting, and conservation efforts. This study examines the relationship between predictors from Landsat-9 remote sensing data several topographical features. While provides reliable crucial for long-term monitoring, it is part of a broader suite available technologies. We employ machine learning algorithms such as Extreme Gradient Boosting (XGBoost), Support Vector Regression (SVR), Random Forest (RF), alongside linear regression techniques like Multiple Linear (MLR). The primary objectives this encompass two key aspects. Firstly, research methodically selects optimal predictor combinations four distinct variable groups: (L1) data, fusion Vegetation-based indices (L2), integration with Shuttle Radar Topography Mission Digital Elevation Model (SRTM DEM) (L3) combination best (L4) derived L1, L2, L3. Secondly, systematically assesses effectiveness different to identify most precise method establishing any potential field-measured AGB variables. Our revealed that (RF) model was utilizing OLI SRTM DEM predictors, achieving remarkable accuracy. conclusion reached by assessing its outstanding performance when compared an independent validation dataset. RF exhibited accuracy, presenting relative mean absolute error (RMAE), root square (RRMSE), R2 values 14.33%, 22.23%, 0.81, respectively. XGBoost subsequent choice RMAE, RRMSE, 15.54%, 23.85%, 0.77, further highlights significance specific spectral bands, notably B4 B5 Landsat 9 capturing spatial distribution patterns. Integration vegetation-based indices, including TNDVI, NDVI, RVI, GNDVI, refines mapping precision. Elevation, slope, Topographic Wetness Index (TWI) are proxies representing biophysical biological mechanisms impacting AGB. Through utilization openly accessible fine-resolution employing algorithm, demonstrated promising outcomes identification predictor-algorithm mapping. comprehensive approach offers valuable avenue informed decision-making assessment, ecological monitoring initiatives.

Язык: Английский

---

Correcting forest aboveground biomass biases by incorporating independent canopy height retrieval with conventional machine learning models using GEDI and ICESat-2 data

Ecological Informatics, Год журнала: 2025, Номер unknown, С. 103045 - 103045

Опубликована: Янв. 1, 2025

Язык: Английский

---

Combining GEDI and sentinel data to estimate forest canopy mean height and aboveground biomass

Ecological Informatics, Год журнала: 2023, Номер 78, С. 102348 - 102348

Опубликована: Окт. 24, 2023

Язык: Английский

---

Forest Aboveground Biomass Estimation and Inventory: Evaluating Remote Sensing-Based Approaches

Forests, Год журнала: 2024, Номер 15(6), С. 1055 - 1055

Опубликована: Июнь 18, 2024

Remote sensing datasets offer robust approaches for gaining reliable insights into forest ecosystems. Despite numerous studies reviewing aboveground biomass estimation using remote approaches, a comprehensive synthesis of synergetic integration methods to map and estimate AGB is still needed. This article reviews the integrated discusses significant advances in estimating from space- airborne sensors. review covers research articles published during 2015–2023 ascertain recent developments. A total 98 peer-reviewed journal were selected under Preferred Reporting Items Systematic Reviews Meta-Analysis (PRISMA) guidelines. Among scrutinized studies, 54 relevant spaceborne, 22 airborne, datasets. empirical models used, random regression model accounted most (32). The highest number utilizing dataset originated China (24), followed by USA (15). datasets, Sentinel-1 2, Landsat, GEDI, Airborne LiDAR widely employed with parameters that encompassed tree height, canopy cover, vegetation indices. results co-citation analysis also determined be objectives this review. focuses on provides accuracy reliability modeling.

Язык: Английский

---

Enhancing carbon stock estimation in forests: Integrating multi-data predictors with random forest method

Ecological Informatics, Год журнала: 2025, Номер unknown, С. 102997 - 102997

Опубликована: Янв. 1, 2025

Язык: Английский

---

Modelling aboveground biomass of a multistage managed forest through synergistic use of Landsat-OLI, ALOS-2 L-band SAR and GEDI metrics

Ecological Informatics, Год журнала: 2023, Номер 77, С. 102234 - 102234

Опубликована: Июль 26, 2023

Язык: Английский

---

Optimising carbon fixation through agroforestry: Estimation of aboveground biomass using multi-sensor data synergy and machine learning

Ecological Informatics, Год журнала: 2023, Номер 79, С. 102408 - 102408

Опубликована: Дек. 3, 2023

As agricultural land expansion is the primary driver of deforestation, agroforestry could be an optimal use strategy for climate change mitigation and reducing pressure on forests. Agroforestry a promising method carbon sequestration. With recent advancements in geospatial data science technology, ability to predict aboveground biomass (AGB) assess ecosystem services rapidly expanding. This study was conducted Belpada Block Balangir, Odisha, forest-dominated region eastern India. We recorded species occurrence measured plant parameters, including Circumference at Breast Height (CBH), height, geolocation, 196 plots (0.09 ha) intervention sites noted tree species. used Sentinel-1 Sentinel-2 multi sensor achieve synergy AGB estimation. Three machine learning models were used: Random Forest (RF), Support Vector Machine (SVM), Artificial Neural Network (ANN). The RF model exhibited highest level prediction accuracy (R2 = 0.69 RMSE 17.07 Mg/ha), followed by ANN 0.63 19.35 SVM 0.54, 21.97 Mg/ha. spectral vegetation indices that are (Normalized Difference Vegetation Index (NDVI), Soil-Adjusted (SAVI), Enhanced (EVI), Modified Simple Ratio (MSR), (MSAVI), (DVI), SAR backscatter values, found important variables prediction. findings revealed interventions plantations resulted average stock increase 15 Mg/ha over five years area. Plant Value (PVI), which indicates importance local economy storage, showed Tectona grandis dominant with PVI value (88.35), Eucalyptus globulus (56.87), Mangifera indica (53.75), Azadirachta (15.45). approach enables monitoring efforts systems, thereby promoting effective management strategies.

Язык: Английский

---

Hybrid machine learning models for aboveground biomass estimations

Ecological Informatics, Год журнала: 2023, Номер 79, С. 102421 - 102421

Опубликована: Дек. 12, 2023

Forest biomass provides a quantitative assessment for carbon stock marketing on national or regional scale. Some countries have committed to net zero emissions, so proper estimations are essential. This study investigates the uses of machine learning (LightGBM, XGBoost), in which hyperparameters were tuned by Bayesian-based Optimisers and novel Tasmanian Devil Optimisation algorithm estimates aboveground (AGB) using Sentinel 1A, Landsat images, ground survey data. A province northern part Vietnam was selected as case since change land cover has been considered crucial. The models optimized/trained validated statistical indicators, namely, root mean square error (RMSE), coefficient determination (R2), absolute (MAE). trained further explained SHAP values understand better how they perform contribution each feature overall estimates. results showed that three indicators proposed model statistically than those reference methods. Specifically, hybrid ended up at RMSE ~13.87, MAE ~ 10.62, R2 0.79 estimation AGB. Based experience, such integration can be recommended an alternative solution estimation. In broader context, fast growth optimization algorithms created new scientifically sound solutions analysis forest cover.

Язык: Английский

---

Mapping of Temporally Dynamic Tropical Forest and Plantations Canopy Height in Borneo Utilizing TanDEM-X InSAR and Multi-sensor Remote Sensing Data

Journal of the Indian Society of Remote Sensing, Год журнала: 2024, Номер unknown

Опубликована: Фев. 5, 2024

Язык: Английский

---

Aboveground biomass inversion of forestland in a Jinsha River dry-hot valley by integrating high and medium spatial resolution optical images: A case study on Yuanmou County of Southwest China

Ecological Informatics, Год журнала: 2024, Номер 83, С. 102796 - 102796

Опубликована: Авг. 25, 2024

It is crucial to develop a comprehensive method for estimating the aboveground biomass (AGB) of trees, shrubs, grasslands, and sparse tree areas in ecologically fragile dry, hot valley regions with vertical zonation. Multi-source remote-sensing data can fulfill this requirement, providing help monitoring health ecosystems basis regional biodiversity conservation restoration. Sentinel-2A satellite imagery was used classify forests, grasslands Yuanmou County, Chuxiong Yi Autonomous Prefecture, Yunnan Province, China. The Gaofen-2 (GF-2) extract canopy width calculate valley-type savanna region. These were combined factors measured survey data, random forest (RF) extreme gradient boosting (XGBoost) models estimate biomass. Using GF-2 images segment effectively reduced overestimation low-resolution images, enabling AGB trees be accurately estimated. estimations based on attained coefficient determination (R2) values 0.45 0.47 forest, 0.55 0.61 0.32 0.37 using RF XGBoost models, respectively, demonstrating variable effectiveness across vegetation types. In addition, model more robust than all three Our methodology provides scientific support sustainable development valleys areas.

Язык: Английский

---