Open research questions in Remote Sensing and LiDAR Applications

What the literature leaves open

• In this work, we present a comprehensive solution for using drones and machine learning to recover meteorite falls. The web application is accessible to the meteorite research community at https://find.gfo.rocks. In the subsections below, we detail some of our anticipated future work and improvements.

  A Cloud-Based Tool for Meteorite Recovery Using Drones and Machine Learning · 2026

• While the system presented in this work is significantly more efficient than traditional searching on foot, we list below some improvements and refinements we envision in the future: • Image recognition software and machine learning models are constantly improving (e.g. Robinson et al., 2025), and we will therefore continue to update the machine learning engine to reduce the number of false positives that users must contend with. • The Stage 4 interface will be improved as a native mobile device application, instead of the current web browser. • Stage 3 of the searching process is not yet implemented in the current web application and could reduce the time spent by team members in the field eliminating false positives. Combining this step with the added capability of a multi-spectral sensor (see below) could further enhance the effectiveness of this step, though this addition could be limited by site- specific factors such as tree coverage and fall site total area. • Multispectral imaging could enable greater discrimination between meteorites and surrounding materials by exploiting different reflectance properties across individual spectral bands. These differences can be enhanced by combining images from individual bands into false color composites, allowing meteorites to appear visually distinctive from their backgrounds as well as some terrestrial rocks (Lovelock et al., 2025). By automating this process, a user could be presented with an image showing meteorites in a distinctive color, supporting more efficient validation and reduction of false positives. Most multispectral sensors have a significantly lower spatial resolution than our survey drone's 48 MP camera, therefore such an approach would likely be best implemented on a follow up drone for Stage 3 searching. • Thermal imaging also offers a potential enhancement for meteorite identification by exploiting differences in thermal inertia between meteorites and common terrestrial materials. Meteorites could be identified by their temperatures following exposure to sunlight, as they retain and release heat at different rates than terrestrial rocks and soils (Lovelock et al., 2025). This approach would require significant development before application in the field, including thermal modeling of meteorites to account for the effect of sample size and cooling influences, such as wind speed and ambient temperature on sample temperature. • While thermal and multi-spectral imaging techniques could help to reduce the number of candidates and assist with searches conducted in more heavily vegetated terrain, especially in Stage 3, we do not anticipate these to fully replace RGB imaging in the survey phase, due to their significantly lower spatial imaging resolution. 16 ACKNOWLEDGEMENTS This research was partially supported by

  A Cloud-Based Tool for Meteorite Recovery Using Drones and Machine Learning · 2026

• the results are context-specific and determined by the sample characteristics, environmental conditions, data sources, spatial scale, temporal setting, and candidate methods, - the study only examined a specific subtropical forest region, - the limited marginal gain from Landsat 8 should be regarded as a context-specific result

  Evaluating the Marginal Contribution of Remote Sensing for Forest Biomass Estimation When Inventory Data Exists · 2026 · DOI

• examining the marginal contribution of optical remote sensing data in other forest regions, - investigating the effects of different data sources and spatial scales on AGB estimation, - developing more accurate and robust models for AGB estimation

  Evaluating the Marginal Contribution of Remote Sensing for Forest Biomass Estimation When Inventory Data Exists · 2026 · DOI

• dataset size and spatial coverage are limited, - the current dataset was collected from paddy fields in Iwamizawa over two consecutive growing seasons, - the training data currently include only one rice variety, Sorayutaka

  Spatiotemporal Deep Learning for Rice Plant Height Estimation from Multi-Temporal UAV RGB Imagery · 2026 · DOI

• further validation using broader multi-regional datasets, - exploring the transferability of Rice-STNet to geographically distant paddy fields and different flooded-field conditions

  Spatiotemporal Deep Learning for Rice Plant Height Estimation from Multi-Temporal UAV RGB Imagery · 2026 · DOI

• the judicious selection of suitable spectral bands tailored to specific applications and existing objects - the technical and commercial constraints of MSL data acquisition - the need for more detailed structural information compared to photogrammetric-based data

  Multispectral Light Detection and Ranging Technology and Applications: A Review · 2024 · DOI

• Future research should focus on improving biomass estimation accuracy by increasing field data collection, utilizing multitemporal remote sensing data, and formulating specific regression equations for each forest type.

  Estimation of the tree aboveground biomass and carbon stock of the Bai Tu Long National Park forest ecosystem from Sentinel-2 images via regression models · 2026 · DOI

• While hybrid architectures combining Transformer Encoders and Graph Neural Networks (GNN) have demonstrated competitive performance in remote sensing classification tasks, the choice of fusion strategy for integrating multi-branch representations remains largely underexplored.

  Comparative analysis of feature fusion strategies in a transformer encoder–GNN framework for Amazon deforestation detection · 2026 · DOI

• However, there is limited information on their comparison, especially in soybean ( Glycine max [L.

  Plant height measurement using UAV-based aerial RGB and LiDAR images in soybean · 2025 · DOI

• Handheld Mobile Laser Scanning (HMLS) offers a rapid alternative for building forest inventories; however, its effectiveness and accuracy in diverse subtropical forests with complex canopy structure remain under-investigated.

  Mapping Individual Tree- and Plot-Level Biomass Using Handheld Mobile Laser Scanning in Complex Subtropical Secondary and Old-Growth Forests · 2025 · DOI

• Some of these studies focus on either onshore or inshore areas using sensors and collecting valuable information that remains unknown and untapped by other researchers.

  A Holistic High-Resolution Remote Sensing Approach for Mapping Coastal Geomorphology and Marine Habitats · 2025 · DOI

• Quantifying the environmental impacts of such initiatives is very important; however, carbon pool data for BTAP plantation regions remain unavailable and are underexplored.

  Estimating Aboveground Biomass and Carbon Sequestration in Afforestation Areas Using Optical/SAR Data Fusion and Machine Learning · 2025 · DOI

• While initial studies suggest that DL models could match or surpass the performance of established classifiers, even on small datasets, the integration of these advanced models into real-time navigation systems on UAVs remains underexplored.

  Unmanned Aerial Vehicles for Real-Time Vegetation Monitoring in Antarctica: A Review · 2025 · DOI

• However, few studies have compared their performance in tree species classification.

  Comparison of UAV-Based LiDAR and Photogrammetric Point Cloud for Individual Tree Species Classification of Urban Areas · 2025 · DOI

• Future studies are recommended to train neural networks with images from various regions to increase generalization and method portability.

  Surveying Nearshore Bathymetry Using Multispectral and Hyperspectral Satellite Imagery and Machine Learning · 2025 · DOI

• Many algorithms have been developed for this purpose based on the Landsat time series, but their nationwide performance across different regions and disturbance types remains unexplored.

  Comprehensive Comparison and Validation of Forest Disturbance Monitoring Algorithms Based on Landsat Time Series in China · 2025 · DOI

• Nonetheless, there is limited research on the combined use of UAS (Uncrewed Aerial System) and Backpack-LiDAR technologies for detailed forest biomass.

  Integration of UAS and Backpack-LiDAR to Estimate Aboveground Biomass of Picea crassifolia Forest in Eastern Qinghai, China · 2025 · DOI

• However, to date, the application of Convolutional Neural Networks (CNNs) for segmentation of mature somatic embryos remains unexplored.

  Deep learning for automated segmentation and counting of hypocotyl and cotyledon regions in mature Pinus radiata D. Don. somatic embryo images · 2024 · DOI

• This review study provides a panoramic view of knowledge in a certain field and reveals the issues that have not been fully explored in the research field of monitoring technologies for potential environmental damage caused by power transmission and transformation projects.

  Research on Environmental Risk Monitoring and Advance Warning Technologies of Power Transmission and Distribution Projects Construction Phase · 2024 · DOI

• While the results are promising, the computational cost of GRFEBK and its performance under varying geographical conditions warrant further investigation at larger scales to assess its broader applicability.

  Estimating Forest Aboveground Biomass Using a Combination of Geographical Random Forest and Empirical Bayesian Kriging Models · 2024 · DOI

• Aquatic ecosystems are crucial in preserving biodiversity, regulating biogeochemical cycles, and sustaining human life; however, their resilience against climate change and anthropogenic stressors remains poorly understood.

  Enhancing Georeferencing and Mosaicking Techniques over Water Surfaces with High-Resolution Unmanned Aerial Vehicle (UAV) Imagery · 2024 · DOI

• This open-source workflow represents a significant advancement in the monitoring of marine and coastal processes, resolving a major limitation facing UAV technology in the remote observation of local-scale phenomena over water surfaces.

  Enhancing Georeferencing and Mosaicking Techniques over Water Surfaces with High-Resolution Unmanned Aerial Vehicle (UAV) Imagery · 2024 · DOI

• Future research should focus on developing robust algorithms and cost-effective solutions to improve measurement accuracy and accessibility.

  Mobile Devices in Forest Mensuration: A Review of Technologies and Methods in Single Tree Measurements · 2024 · DOI

• However, three questions remain to be answered: first, which of the state-of-the-art models performs best for this task; second, which is the optimal season for tree species classification in a temperate forest; and third, whether a model trained in one season can be effectively transferred to another season.

  Tree Species Classification from UAV Canopy Images with Deep Learning Models · 2024 · DOI

Most-cited papers in Remote Sensing and LiDAR Applications

• Lidar Remote Sensing for Ecosystem Studies · BioScience · 2002 · 1,391 citations
• Dawn of Drone Ecology: Low-Cost Autonomous Aerial Vehicles for Conservation · Tropical Conservation Science · 2012 · 514 citations
• Aboveground biomass density models for NASA’s Global Ecosystem Dynamics Investigation (GEDI) lidar mission · Remote Sensing of Environment · 2022 · 454 citations
• Green streets − Quantifying and mapping urban trees with street-level imagery and computer vision · Landscape and Urban Planning · 2017 · 292 citations
• Remote sensing in forestry: current challenges, considerations and directions · Forestry An International Journal of Forest Research · 2023 · 259 citations
• Extracting urban features from LiDAR digital surface models · Computers Environment and Urban Systems · 2000 · 225 citations
• Review of Remote Sensing-Based Methods for Forest Aboveground Biomass Estimation: Progress, Challenges, and Prospects · Forests · 2023 · 216 citations
• Automated derivation of urban building density information using airborne LiDAR data and object-based method · Landscape and Urban Planning · 2010 · 196 citations
• Predicting scenic beauty of mountain regions · Landscape and Urban Planning · 2013 · 196 citations
• The potential of airborne lidar for detection of archaeological features under woodland canopies · Antiquity · 2005 · 180 citations

Most recent work

• Research progress on multimodal data fusion in forest resource monitoring · Frontiers in Plant Science · 2026
• Semiparametric Estimation of the Shape of the Limiting Bivariate Point Cloud · Bayesian Analysis · 2026
• Estimation of the tree aboveground biomass and carbon stock of the Bai Tu Long National Park forest ecosystem from Sentinel-2 images via regression models · Discover Sustainability · 2026
• Application of UAV multimodal data and deep learning for estimating soil salt content at the small catchment scale · International Soil and Water Conservation Research · 2026
• Mapping forest road surface deterioration: detection, localization, and assessing maintenance features with the near-field sensor platform RoadSens · International Journal of Forest Engineering · 2026
• Three-dimensional green quantity (3DGQ) mapping and integrated 2D–3D assessment reveal hidden urban green deficits and inequities · Journal of Environmental Management · 2026
• Integration of multi-source point clouds for bridge inventory – case study · The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences · 2026
• LiDAR in precision agriculture for orchards and perennial tree crops: bibliometric analysis, sensor technologies, and algorithmic workflows · Computers and Electronics in Agriculture · 2026
• A novel two-step framework for bush biomass change-detection and quantification in Namibia using ground- and drone-based LiDAR - a pilot study · Biomass and Bioenergy · 2026
• Where Are the City Trees? Monitoring Urban Trees across the U.S. Using Generative AI · Communications of the ACM · 2026

Related topics in Environmental Science