Enhancing Tree Species Mapping in Arkansas' Forests through Machine Learning and Satellite Data Fusion: A Google Earth Engine-Based Approach DOI Creative Commons

Abdullah Al Saim,

Mohamed H. Aly

Research Square (Research Square), Год журнала: 2024, Номер unknown

Опубликована: Дек. 2, 2024

Abstract Arkansas' subtropical climate nurtures extensive forested regions, particularly within the Ozark- St. Francis and Ouachita National Forests. Despite this, state lacks an up-to-date, high-resolution map detailing distribution of tree species its forests. This study harnesses power machine learning, specifically Random Forest (RF), Gradient Tree Boosting (GTB), Support Vector Machine (SVM), K-Nearest Neighbors (K-NN) classifiers, Google Earth Engine (GEE) framework. These classifiers are applied to classify in forests by integrating data from various sources, including Sentinel-1/-2, Landsat-8, Agriculture Imagery Program (NAIP). The evaluates classification accuracy single-sensor images against fused composites, revealing that Landsat-8 Sentinel-1 achieve highest validation at 0.8875. is closely followed which yield accuracies 0.8863 0.8859, respectively. Among RF demonstrates accuracy, GTB, K-NN, SVM when images. incorporates Shapley Additive Explanations (SHAP) elucidate feature importance introduces a weighted ensemble method, resulting remarkably accurate with score 0.9772. research highlights efficacy combining learning algorithms fusing satellite significantly enhance accuracy. Moreover, capitalizes on explainable AI (XAI) principles leverages cloud computing capabilities GEE create more precise, cover regional scale.

Язык: Английский

Optimal Integration of Optical and SAR Data for Improving Alfalfa Yield and Quality Traits Prediction: New Insights into Satellite-Based Forage Crop Monitoring DOI Creative Commons
Jiang Chen, Tong Yu, J. H. Cherney

и другие.

Remote Sensing, Год журнала: 2024, Номер 16(5), С. 734 - 734

Опубликована: Фев. 20, 2024

Global food security and nutrition is suffering from unprecedented challenges. To reach a world without hunger malnutrition by implementing precision agriculture, satellite remote sensing plays an increasingly important role in field crop monitoring management. Alfalfa, global widely distributed forage crop, requires more attention to predict its yield quality traits data since it supports the livestock industry. Meanwhile, there are some key issues that remain unknown regarding alfalfa optical synthetic aperture radar (SAR) data. Using Sentinel-1 Sentinel-2 data, this study developed, compared, further integrated new optical- SAR-based models for improving prediction, i.e., crude protein (CP), acid detergent fiber (ADF), neutral (NDF), digestibility (NDFD). better understand physical mechanism of sensing, unified hybrid leaf area index (LAI) retrieval scheme was developed coupling PROSAIL radiative transfer model, spectral response function desired satellite, random forest (RF) denoted as scalable satellite-based LAI framework. Compared vegetation indices (VIs) only capture canopy information, results indicate had highest correlation (r = 0.701) with due capacity delivering structure characteristics. For traits, chlorophyll VIs presented higher correlations than LAI. On other hand, did not provide significant additional contribution predicting parameters RF prediction model using inputs. In addition, optical-based outperformed yield, CP, NDFD, while showed performance ADF NDF. The integration SAR contributed accuracy either or separately. traditional embedded approach, combination multisource heterogeneous satellites optimized multiple linear regression (yield: R2 0.846 RMSE 0.0354 kg/m2; CP: 0.636 1.57%; ADF: 0.559 1.926%; NDF: 0.58 2.097%; NDFD: 0.679 2.426%). Overall, provides insights into large-scale fields satellites.

Язык: Английский

Процитировано

10
A critical review on multi-sensor and multi-platform remote sensing data fusion approaches: current status and prospects DOI Creative Commons
Farhad Samadzadegan, Ahmad Toosi, Farzaneh Dadrass Javan

и другие.

International Journal of Remote Sensing, Год журнала: 2024, Номер unknown, С. 1 - 76

Опубликована: Дек. 11, 2024

Numerous remote sensing (RS) systems currently collect data about Earth and its environments. However, each system provides limited in terms of spatial resolution, spectral information, other parameters. Given technological constraints, combining from diverse sources can effectively enhance RS solutions through enrichment. Many studies have investigated the fusion acquired different sensors platforms. This paper a comprehensive review research on multi-platform -sensor fusion, encompassing visible-light images, multi/hyper-spectral RADAR LiDAR point clouds, thermal spectrometry samples, geophysical data. An analysis over 950 papers revealed that feature-level multi-sensor was most commonly employed technique, surpassing pixel- decision-level approaches. Moreover, satellite more prevalent than manned unmanned aerial vehicles. The integration initially gained traction applications such as precision agriculture before expanding to land use cover mapping. addresses previously overlooked issues presents framework facilitate seamless Guidelines for this include ensuring same acquisition time, co-registration, true orthorectification, consistent resolution or information content, radiometric consistency, wavelength band coverage.

Язык: Английский

Процитировано

8
Fusion-Based Approaches and Machine Learning Algorithms for Forest Monitoring: A Systematic Review DOI Open Access

Abdullah Al Saim,

Mohamed H. Aly

Wild, Год журнала: 2025, Номер 2(1), С. 7 - 7

Опубликована: Март 11, 2025

Multi-source remote sensing fusion and machine learning are effective tools for forest monitoring. This study aimed to analyze various techniques, their application with algorithms, assessment in estimating type aboveground biomass (AGB). A keyword search across Web of Science, Science Direct, Google Scholar yielded 920 articles. After rigorous screening, 72 relevant articles were analyzed. Results showed a growing trend optical radar fusion, notable use hyperspectral images, LiDAR, field measurements fusion-based Machine particularly Random Forest (RF), Support Vector (SVM), K-Nearest Neighbor (KNN), leverage features from fused sources, proper variable selection enhancing accuracy. Standard evaluation metrics include Mean Absolute Error (MAE), Root Squared (RMSE), Overall Accuracy (OA), User’s (UA), Producer’s (PA), confusion matrix, Kappa coefficient. review provides comprehensive overview prevalent data by synthesizing current research highlighting fusion’s potential improve monitoring The underscores the importance spectral, topographic, textural, environmental variables, sensor frequency, key gaps standardized protocols exploration multi-temporal dynamic change

Язык: Английский

Процитировано

1
Improving the estimation accuracy of alfalfa quality based on UAV hyperspectral imagery by using data enhancement and synergistic band selection strategies DOI
Shuai Fu, Jie Liu, Jinlong Gao

и другие.

Computers and Electronics in Agriculture, Год журнала: 2025, Номер 234, С. 110305 - 110305

Опубликована: Март 19, 2025

Язык: Английский

Процитировано

1
Digital mapping of soil salinity with time-windows features optimization and ensemble learning model DOI Creative Commons
Shuaishuai Shi, Nan Wang, Songchao Chen

и другие.

Ecological Informatics, Год журнала: 2024, Номер unknown, С. 102982 - 102982

Опубликована: Дек. 1, 2024

Язык: Английский

Процитировано

4
Research on the impact and mechanism of digital economy on China’s food production capacity DOI Creative Commons
Jue Wang, Yanyan Dong, Heng Wang

и другие.

Scientific Reports, Год журнала: 2024, Номер 14(1)

Опубликована: Ноя. 8, 2024

Enhancing and strengthening food production capacity has always been a top priority in agricultural research, serving as cornerstone for ensuring national security stable economic development. This study, based on panel data spanning from 2011 to 2021 across 30 provinces China, delves into the mechanism through which digital economy impacts capacity. Employing double fixed effect model, mediation threshold we uncover several key findings: The significantly boosts capacity, with robustness tests affirming reliability of our results. Mechanism analysis reveals that enhances by elevating total factor productivity bolstering resilience. underscores urbanization levels exhibit single-threshold impact, wherein influence intensifies upon crossing this threshold. Heterogeneity central primary grain-producing regions, while its impact is comparatively weaker eastern western well non-primary areas. In summary, research sheds light pivotal role augmenting offering valuable insights regional variations thresholds China.

Язык: Английский

Процитировано

3
Temporal segmentation method for 30-meter long-term mapping of abandoned and reclaimed croplands in Inner Mongolia, China DOI Creative Commons
Deji Wuyun, Liang Sun, Zhongxin Chen

и другие.

International Journal of Applied Earth Observation and Geoinformation, Год журнала: 2025, Номер 136, С. 104399 - 104399

Опубликована: Фев. 1, 2025

Язык: Английский

Процитировано

0
Alfalfa yield estimation using the combination of Sentinel-2 and meteorological data DOI Creative Commons
Angie L. Gámez, Joel Segarra, Thomas Vatter

и другие.

Field Crops Research, Год журнала: 2025, Номер 326, С. 109857 - 109857

Опубликована: Март 19, 2025

Язык: Английский

Процитировано

0
Crop Mapping and Monitoring Using Sentinel-2: A Review DOI

Kenzie M. Prado,

Luis Alberto Riancho Martín,

Rheyent L. Boton

и другие.

Smart innovation, systems and technologies, Год журнала: 2025, Номер unknown, С. 173 - 185

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

0
Improving the estimation of alfalfa yield based on multi-source satellite data and the synthetic minority oversampling strategy DOI

Lanxiang Li,

Shuai Fu, Jinlong Gao

и другие.

Computers and Electronics in Agriculture, Год журнала: 2025, Номер 236, С. 110497 - 110497

Опубликована: Май 9, 2025

Язык: Английский

Процитировано

0