A Review of Deep Learning Approach for Analyzing Remote Sensing Spectral Data in Species

International Journal of Electrical and Electronics Engineering

© 2025 by SSRG - IJEEE Journal

Volume 12 Issue 5

Year of Publication : 2025

Authors : Nita Nimbarte, Vandana Katna, Sanjay Balamwar

10.14445/23488379/IJEEE-V12I5P105

How to Cite?

Nita Nimbarte, Vandana Katna, Sanjay Balamwar, "A Review of Deep Learning Approach for Analyzing Remote Sensing Spectral Data in Species," SSRG International Journal of Electrical and Electronics Engineering, vol. 12,  no. 5, pp. 45-57, 2025. Crossref, https://doi.org/10.14445/23488379/IJEEE-V12I5P105

Abstract:

Remote sensing technologies have become crucial for forest management, providing large-scale data through satellite and aerial imagery. Automated semantic segmentation of trees enables efficient monitoring, although the task remains challenging due to varying tree spectral signatures, the limited availability of labeled datasets, and geometric distortions. In the domain of precision agriculture, major research efforts have focused on monitoring agricultural fields, classifying land use, and optimizing crop yields. In terms of accuracy and reliability, deep learning algorithms now perform noticeably better than conventional machine learning techniques for remote sensing image analysis. Recent advances in image segmentation, a key field in computer vision, have enabled more accurate identification and categorization of objects in remote sensing images. While many studies rely on frontal or asymmetrical image views, this review focuses on deep-learning approaches using top-down datasets for species and land cover segmentation. Models such as U-Net, SiU-Net, and DeepLabV3+ demonstrate notable performance improvements, achieving mean average precisions of 0.921, 0.970, and 0.976, respectively. Compared to earlier conventional approaches, these models show a significant leap in accuracy, particularly in handling fine-grained details and large-scale environmental variations. Furthermore, independent validation using tree species proportion maps highlights the practical reliability of these models in estimating species presence, absence, and distribution, thereby reinforcing their importance in advancing remote sensing-based ecological and agricultural monitoring.

Keywords:

Remote Sensing, Multispectral Data, Hyperspectral Data, Deep Learning, Image Classification.

References:

[1] Won-Kyung Baek, Moung-Jin Lee, and Hyung-Sup Jung, “Land Cover Classification from RGB and NIR Satellite Images Using Modified U-Net Model,” IEEE Access, vol. 12, pp. 69445-69455, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Corentin Bolyna et al., “Mapping Tree Species Proportions from Satellite Imagery using Spectral-Spatial Deep Learning,” Remote Sensing of Environment, vol. 280, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Suzanna Cuypers, Andrea Nascetti, and Maarten Vergauwen, “Land Use and Land Cover Mapping with VHR and Multi-Temporal Sentinel-2 Imagery,” Remote Sensing, vol. 15, no. 10, pp. 1-16, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Irem Ulku, Erdem Akagündüz, and Pedram Ghamisi, “Deep Semantic Segmentation of Trees Using Multispectral Images,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 15, pp. 7589-7604, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Furkat Safarov et al., “Improved Agricultural Field Segmentation in Satellite Imagery Using TL-ResUNet Architecture,” Sensors, vol. 22, no. 24, pp. 1-15, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Javier Marcello et al., “Advanced Processing of Multiplatform Remote Sensing Imagery for the Monitoring of Coastal and Mountain Ecosystems,” IEEE Access, vol. 9, pp.  6536-6549, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Man Liu et al., “Comparison of Multi-Source Satellite Images for Classifying Marsh Vegetation using DeepLabV3 Plus Deep Learning Algorithm,” Ecological Indicators, vol. 125, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Kunhao Yuan et al., “Deep-Learning-Based Multispectral Satellite Image Segmentation for Water Body Detection,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 14, pp. 7422-7434, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Md Osman Gani et al., “Multispectral Object Detection with Deep Learning,” International Conference on Computational Intelligence in Communications and Business Analytics, Santiniketan, India, pp. 105-117, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Islombek Mirpulatov et al., “Pseudo-Labeling Approach for Land Cover Classification Through Remote Sensing Observations with Noisy Labels,” IEEE Access, vol. 11, pp. 82570-82583, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Imran Ahmed et al., “Comparison of Deep-Learning-Based Segmentation Models: Using Top View Person Images,” IEEE Access, vol. 8, pp. 136361-136373, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[12] G. D’Amico et al., “A Deep Learning Approach for Automatic Mapping of Poplar Plantations using Sentinel-2 Imagery,” GIScience & Remote Sensing, vol. 58, no. 8, pp. 1352-1368, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Hamid Ghanbari et al., “A Meta-Analysis of Convolutional Neural Networks for Remote Sensing Applications,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 14, pp. 3602-3613, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Nicolas Latte, and Philippe Lejeune, “Planet Scope Radiometric Normalization and Sentinel-2 Super-Resolution (2.5 m): A Straight Forward Spectral-Spatial Fusion of Multi-Satellite Multi-Sensor Images Using Residual Convolutional Neural Networks,” Remote Sensing, vol. 12, no. 15, pp. 1-19, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Kristian Skau Bjerreskov, Thomas Nord-Larsen, and RasmusFensholt, “Classification of Nemoral Forests with Fusion of Multi-Temporal Sentinel-1 and 2 Data,” Remote Sensing, vol. 13, no. 5, pp. 1-19, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Janne Mäyrä, et al “Tree Species Classification from Airborne Hyperspectral and LiDAR Data using 3D Convolutional Neural Networks,” Remote Sensing of Environment, vol. 256, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Nicola Clerici, Cesar Augusto Valbuena Calderón, and Juan Manuel Posada, “Fusion of Sentinel-1A and Sentinel-2A Data for Land Cover Mapping: A Case Study in the Lower Magdalena Region, Colombia,” Journal of Maps, vol. 13, no. 2, pp. 718-726, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Thomas Blaschke et al., “Geographic Object-Based Image Analysis-Towards a New Paradigm,” ISPRS Journal of Photogrammetry and Remote Sensing, vol. 87, pp. 180-191, 2013.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Giandomenico De Luca et al., “Integrated Use of Sentinel-1 and Sentinel-2 Data and Open-Source Machine Learning Algorithms for Land Cover Mapping in a Mediterranean Region,” European Journal of Remote Sensing, vol. 55, no. 1, pp. 52-70, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[20] “Maher Ibrahim Sameen, Biswajeet Pradhan, and OmarSaud Aziz, “Classification of Very High-Resolution Aerial Photos Using Spectral-Spatial Convolutional Neural Networks,” Hindawi Journal of Sensors, vol. 2018, no. 1, pp. 1-12, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Abdulhakim Mohamed Abdi, “Land Cover and Land Use Classification Performance of Machine Learning Algorithms in a Boreal Landscape using Sentinel-2 Data,” GIScience & Remote Sensing, vol. 57, no. 1, pp. 1-20, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Andrew J. Chadwick et al., “Species Classification of Automatically Delineated Regenerating Conifer Crowns Using RGB and Near-Infrared UAV Imagery,” IEEE Geoscience and Remote Sensing Letters, vol. 19, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Yu-Kai Chen, Keng-Hao Liu, and Chinsu Lin, “Plant Species Recognition based on Hyperspectral Plant Canopy Images with Deep Learning,” IEEE International Geoscience and Remote Sensing Symposium, Pasadena, CA, USA, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Enoch Gyamfi-Ampadu, Michael Gebreslasie, and Alma Mendoza-Ponce, “Evaluating Multi-Sensors Spectral and Spatial Resolutions for Tree Species Diversity Prediction,” Remote Sensing, vol. 13, no. 5, pp. 1-18, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Junhwa Chi et al., “Spectral Characteristics of the Antarctic Vegetation: A Case Study of Barton Peninsula,” Remote Sensing, vol. 13, no. 13, pp. 1-21, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[26] Xu Wang et al., “Analysis of Vegetation Canopy Spectral Features and Species Discrimination in Reclamation Mining Area Using in Situ Hyperspectral Data,” Remote Sensing, vol. 16, no. 13, pp. 1-22, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[27] Qingyu Li et al., “Building Footprint Generation by Integrating Convolution Neural Network with Feature Pairwise Conditional Random Field (FPCRF),” IEEE Transactions on Geoscience and Remote Sensing, vol. 58, no. 11, pp. 7502-7519, 2020. [CrossRef] [Google Scholar] [Publisher Link]
[28] Nadir Bengana, and Janne Heikkila, “Improving Land Cover Segmentation Across Satellites Using Domain Adaptation,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol.14, pp. 1399-1410, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[29] Vladimir Iglovikov, Sergey Mushinskiy, and Vladimir Osin, “Satellite Imagery Feature Detection using Deep Convolutional Neural Network: A Kaggle Competition,” arXiv Preprint, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[30] Akmalbek Bobomirzaevich Abdusalomov et al., “Improved Feature Parameter Extraction from Speech Signals Using Machine Learning Algorithm,” Sensors, vol. 22, no. 21, pp. 1-21, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[31] Long, Jonathan, Evan Shelhamer, and Trevor Darrell, “Fully Convolutional Networks for Semantic Segmentation,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431-3440, 2015.
[Google Scholar] [Publisher Link]
[32] Honglin Wu et al., “Remote Sensing Image Sharpening by Integrating Multispectral Image Super Resolution and Convolutional Sparse Representation Fusion,” IEEE Access, vol. 7, pp. 46562-46574, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[33] Thomas Lacombea, Hugues Favrelierea, and Maurice Pilleta, “Modal Features for Image Texture Classification,” Pattern Recognition Letters, vol. 135, pp. 249-255, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[34] Riyaaz Uddien Shaik, Shoba Periasamy, and Weiping Zeng, “Potential Assessment of PRISMA Hyperspectral Imagery for Remote Sensing Applications,” Remote Sensing, vol. 15, no. 5, pp. 1-14, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[35] Xiankun Hao et al., “A No-Reference Quality Assessment Method for Hyperspectral Sharpened Images via Benford’s Law,” Remote Sensing, vol. 16, no. 7, pp. 1-32, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[36] Sean Hartling et al., “Urban Tree Species Classification Using a WorldView-2/3 and LiDAR Data Fusion Approach and Deep Learning,” Sensors, vol. 19, no. 6, pp. 1-23, 2019.
[CrossRef] [Google Scholar] [Publisher Link]