Map Of Environment Research Articles

Autonomous navigation system for greenhouse tomato picking robots based on laser SLAM

Aiming at the specific operation path cruising problem of greenhouse tomato picking robots, this paper designs a laser SLAM (Simultaneous Localization And Mapping)-based autonomous navigation system for greenhouse tomato picking robots.The autonomous navigation system utilizes LiDAR to detect the greenhouse environment, creates an environment map with the Gmapping algorithm employing particle filtering, locates the robot with the AMCL (Adaptive Monte Carlo Localization) algorithm, devises the robot's path for picking tasks with the A* algorithm, and dynamically navigates around obstacles during operations with the DWA (Dynamic Window Approach) algorithm. The greenhouse experiment revealed that the robot's average deviance for both directions (X and Y) is 2.87 and 0.80 centimeters, respectively, when traveling a 320 centimeter path. On the other hand, its average variation across the directions of X and Y is 1.48 versus 1.08 centimeters when it passes through a 40 centimeter zone. The robot exhibits averaged variations of 1.73 and 2.24 millimeters in the X and Y axes, each, when navigating a 40-centimeter-radius turn. Furthermore, the robot exhibits average variations of 1.12 centimeters in the X and 0.78 centimeters in the Y directions when it follows a certain "S"-shaped course. Based on the fulfillment of prescribed path cruising, the system has a high level of navigation and positioning accuracy, better meeting the requirements for greenhouse tomato harvesting robot direction and placement.

Multiscale spatiotemporal characterisation of embodied environmental performance of building structures in Geneva from 1850 to 2018

Load-bearing systems in buildings, significant in material use and embodied greenhouse gas emissions (EGHGE), have lacked detailed analysis on their environmental and functional relationships over time and space. This study evaluates the environmental impacts of building structures in Geneva, Switzerland, considering factors like material usage, EGHGE, and urban development. A new method using a similarity-weighted function projects environmental impacts onto a GIS-based building stock, analysing 48 archetypal and 84,477 stock buildings built from 1850 to 2018. Results show a 37% reduction in structural volume per floor area and a 10% increase in mass over time. Buildings predating the masonry-to-concrete transition would produce 7% more EGHGE if constructed today. Multi-residential buildings emit 14% less EGHGE than single homes. A new indicator amortizes upfront environmental effects over a building's lifespan, aiding in historical comparisons of building stocks. This approach underscores the need for spatial-temporal environmental impact mapping to understand sustainable urban development dynamics.

Bridging depths and data in mines: 5G-based point cloud mapping in unstructured environments

Underground mines pose significant challenges, including hazardous working conditions, limited access, and the need to ensure the safety of human workers. Digital transformation through the integration of modern technologies is essential to mitigate these challenges and enhance the overall safety and efficiency of mining operations. This paper addresses the pressing need for 5G connectivity for the digital transformation of underground mines and demonstrates its application through a live 3D point cloud mapping by a mobile robot. The results of the experiments conducted to validate the network’s performance for such a use-case are presented. The first experiment involved testing the latency of the network over a test drift at various loads. The second experiment involved mapping the drift and streaming the 3D point cloud map of the drift over the 5G network. These initial experiments emphasize the potential of the 5G-enabled automation in underground mines and holds promise in digitalizing underground mining operations.

Gross depositional environment mapping in the onshore South Australian Otway Basin: an example of data integration

As part of a greater petroleum systems modelling project, gross depositional environment maps were made for six key intervals in the onshore portion of the Jurassic to Late-Cretaceous Otway Basin in South Australia. This mapping interpreted varied depositional systems including anoxic, extensive ice-influenced lacustrine, lacustrine turbidite, extensive fluvial/lacustrine, fluvial/flood plain and growth fault-bound ribbon-like alluvial fan aprons.

Shipwreck and Sherbrook supersequence regional gross depositional environments, offshore Otway Basin

The Shipwreck and Sherbrook supersequences together constitute the upper Cretaceous succession in the Otway Basin that was deposited during an extensional basin phase. In the Shipwreck Trough, where the upper Cretaceous succession is well explored, gas fields are hosted by the Shipwreck Supersequence (SS). Elsewhere, the upper Cretaceous interval is lightly explored, and the deep-water area is considered an exploration frontier. We present regional gross depositional environment (RGDE) maps for the LC1.1 and LC1.2 sequences of the Shipwreck SS, and the LC2 Sherbrook SS. Fluvial Plain, Coastal-Delta Plain and Shelf RGDEs were interpreted from wireline logs, cores, and seismic facies. The Fluvial Plain and Coastal-Delta Plain RGDEs are mostly restricted to the inboard platform areas and the inner Morum Sub-basin. The mud-prone Shelf RGDE is widespread across the deep-water Morum and Nelson depocentres. The extent of the Fluvial and Coastal-Delta Plain belts progressively increases up-section, imparting a regressive aspect to the succession, and delineating a large fluvial-deltaic complex in the north-west of the basin. Thick seal development across the greater Shipwreck Trough, potentially mature source rocks in the deep-water basin, and thick reservoir development in the hanging wall of growth faults in the inner Morum Sub-basin are insights derived from this study, and will inform area selection for detailed gross depositional environment mapping, formulation of new hydrocarbon and carbon dioxide storage plays, and inputs for petroleum systems modelling.

Enhanced Detection of Artisanal Small-Scale Mining with Spectral and Textural Segmentation of Landsat Time Series

Artisanal small-scale mines (ASMs) in the Amazon Rainforest are an important cause of deforestation, forest degradation, biodiversity loss, sedimentation in rivers, and mercury emissions. Satellite image data are widely used in environmental decision-making to monitor changes in the land surface, but ASMs are difficult to map from space. ASMs are small, irregularly shaped, unevenly distributed, and confused (spectrally) with other land clearance types. To address this issue, we developed a reliable and efficient ASM detection method for the Tapajós River Basin of Brazil—an important gold mining region of the Amazon Rainforest. We enhanced detection in three key ways. First, we used the time-series segmentation (LandTrendr) Google Earth Engine (GEE) Application Programming Interface to map the pixel-wise trajectory of natural vegetation disturbance and recovery on an annual basis with a 2000 to 2019 Landsat image time series. Second, we segmented 26 textural features in addition to 5 spectral features to account for the high spatial heterogeneity in ASM pixels. Third, we trained and tested a Random Forest model to detect ASMs after eliminating irrelevant and redundant features with the Variable Selection Using Random Forests “ensemble of ensembles” technique. The out-of-bag error and overall accuracy of the final Random Forest was 3.73 and 92.6%, which are comparable to studies mapping large industrial mines with the normalized difference vegetation index (NDVI) and LandTrendr. The most important feature in our study was NDVI, followed by textural features in the near and shortwave infrared. Our work paves the way for future ASM regulation through large area monitoring from space with free and open-source GEE and operational satellites. Studies with sufficient computational resources can improve ASM monitoring with advanced sensors consisting of spectral narrow bands (Sentinel-2, Environmental Mapping and Analysis Program, PRecursore IperSpettrale della Missione Applicativa) and deep learning.

Research on autonomous navigation system of greenhouse electric crawler tractor based on LiDAR.

The application of autonomous navigation technology of electric crawler tractors is an important link in the development of intelligent greenhouses. Aiming at the characteristics of enclosed and narrow space and uneven ground potholes in greenhouse planting, to improve the intelligence level of greenhouse electric crawler tractors, this paper develops a navigation system of electric crawler tractors for the greenhouse planting environment based on LiDAR technology. The navigation hardware system consists of five modules: the information perception module, the control module, the communication module, the motion module, and the power module. The software system is composed of three layers: the application layer, the data processing layer, and the execution layer. The developed navigation system uses LiDAR, Inertial Measurement Unit (IMU) and wheel speed sensor to sense the greenhouse environment and the crawler tractor's information, employs the Gmapping algorithm to build the greenhouse environment map, and utilizes the adaptive Monte Carlo positioning algorithm for positioning. The simulation test of different global path planning algorithms in Matlab shows that the A* algorithm obtains the optimal overall global path. In the scene of map 5, the path planned by the A* algorithm is the most significant, and the number of inflection points is reduced by 40.00% and 87.50%, respectively; meanwhile, the path length is the same as that of the Dijkstra algorithm, but the runtime is reduced by 68.87% and 81.49%, respectively; compared with the RRT algorithm, the path length is reduced by 7.27%. Therefore, the A* algorithm and the Dynamic Window Approach (DWA) method are used for tractor navigation and obstacle avoidance, which ensures global path optimality while also achieving effective local path planning for obstacle avoidance. The test results suggest that the maximum lateral deviation of the built map is 6cm, and the maximum longitudinal deviation is 16cm, which meets the requirement of map accuracy. Additionally, the results of the navigation accuracy test indicate that the maximum lateral deviation of navigation is less than 13cm, the average lateral deviation is less than 7cm, and the standard lateral deviation is less than 8cm. The maximum heading deviation is less than 14°, the average heading deviation is less than 7°, and the standard deviation is less than 8°. These results show that the developed navigation system meets the navigation accuracy requirements of electric crawler tractors in the greenhouse environment.

Novel Learning of Bathymetry from Landsat 9 Imagery Using Machine Learning, Feature Extraction and Meta-Heuristic Optimization in a Shallow Turbid Lagoon

Bathymetry data is indispensable for a variety of aquatic field studies and benthic resource inventories. Determining water depth can be accomplished through an echo sounding system or remote estimation utilizing space-borne and air-borne data across diverse environments, such as lakes, rivers, seas, or lagoons. Despite being a common option for bathymetry mapping, the use of satellite imagery faces challenges due to the complex inherent optical properties of water bodies (e.g., turbid water), satellite spatial resolution limitations, and constraints in the performance of retrieval models. This study focuses on advancing the remote sensing based method by harnessing the non-linear learning capabilities of the machine learning (ML) model, employing advanced feature selection through a meta-heuristic algorithm, and using image extraction techniques (i.e., band ratio, gray scale morphological operation, and morphological multi-scale decomposition). Herein, we validate the predictive capabilities of six ML models: Random Forest (RF), Support Vector Machine (SVM), CatBoost (CB), Extreme Gradient Boost (XGB), Light Gradient Boosting Machine (LGBM), and KTBoost (KTB) models, both with and without the application of meta-heuristic optimization (i.e., Dragon Fly, Particle Swarm Optimization, and Grey Wolf Optimization), to accurately ascertain water depth. This is achieved using a diverse input dataset derived from multi-spectral Landsat 9 imagery captured on a cloud-free day (19 September 2023) in a shallow, turbid lagoon. Our findings indicate the superior performance of LGBM coupled with Particle Swamp Optimization (R2 = 0.908, RMSE = 0.31 m), affirming the consistency and reliability of the feature extraction and selection-based framework, while offering novel insights into the expansion of bathymetric mapping in complex aquatic environments.

DSOMF: A Dynamic Environment Simultaneous Localization and Mapping Technique Based on Machine Learning.

To address the challenges of reduced localization accuracy and incomplete map construction demonstrated using classical semantic simultaneous localization and mapping (SLAM) algorithms in dynamic environments, this study introduces a dynamic scene SLAM technique that builds upon direct sparse odometry (DSO) and incorporates instance segmentation and video completion algorithms. While prioritizing the algorithm's real-time performance, we leverage the rapid matching capabilities of Direct Sparse Odometry (DSO) to link identical dynamic objects in consecutive frames. This association is achieved through merging semantic and geometric data, thereby enhancing the matching accuracy during image tracking through the inclusion of semantic probability. Furthermore, we incorporate a loop closure module based on video inpainting algorithms into our mapping thread. This allows our algorithm to rely on the completed static background for loop closure detection, further enhancing the localization accuracy of our algorithm. The efficacy of this approach is validated using the TUM and KITTI public datasets and the unmanned platform experiment. Experimental results show that, in various dynamic scenes, our method achieves an improvement exceeding 85% in terms of localization accuracy compared with the DSO system.

A Study on a Health Impact Assessment and Healthcare Cost Calculation of Beijing–Tianjin–Hebei Residents under PM2.5 and O3 Pollution

Excessive fine particulate matter (PM2.5) and ozone (O3) are invisible killers affecting our wellbeing and safety, which cause great harm to people’s health, cause serious healthcare and economic losses, and affect the sustainable development of the social economy. The effective evaluation of the impact of pollutants on the human body, the associated costs, and the reduction of regional compound air pollution is an important research direction. Taking Beijing–Tianjin–Hebei (BTH) as the research area, this study constructs a comprehensive model for measuring the healthcare costs of PM2.5 and O3 using the Environmental Benefits Mapping and Analysis Program (BenMAP) as its basis. First, this study establishes a health impact assessment model and calculates the number of people affected by PM2.5 and O3 exposure using the health impact function in the BTH region. Then, the willingness to pay (WTP) and cost of illness (COI) methods are used to estimate the healthcare costs inflicted by the two pollutants upon residents from 2018 to 2021. The calculation results show that the total healthcare costs caused by PM2.5 and O3 pollution in BTH accounted for 1%, 0.7%, 0.5%, and 0.3% of the regional GDP in 2018, 2019, 2020, and 2021, respectively. Based on the research results, to further reduce these high healthcare costs, we propose policy suggestions for PM2.5 and O3 control in the BTH region.

An Aerial Robotic Missing-Person Search in Urban Settings—A Probabilistic Approach

Autonomous robotic teams have been proposed for a variety of lost-person searches in wilderness and urban settings. In the latter scenarios, for missing persons, the application of such teams, however, is more challenging than it would be in the wilderness. This paper, specifically, examines the application of an autonomous team of unmanned aerial vehicles (UAVs) to perform a sparse, mobile-target search in an urban setting. A novel multi-UAV search-trajectory planning method, which relies on the prediction of the missing-person’s motion, given a known map of the search environment, is the primary focus. The proposed method incorporates periodic updates of the estimates of where the lost/missing person may be, allowing for intelligent re-coverage of previously searched areas. Additional significant contributions of this work include a behavior-based motion-prediction method for missing persons and a novel non-parametric estimator for iso-probability-based (missing-person-location) curves. Simulated experiments are presented to illustrate the effectiveness of the proposed search-planning method, demonstrating higher rates of missing-person detection and in shorter times compared to other methods.

Optimizing offshore wind export cable routing using GIS-based environmental heat maps

Abstract. In the United States, there are plans to produce up to 30 GW of offshore wind power by the year 2030, resulting in numerous seabed lease areas which are currently going through the leasing or construction and operations phase. A key challenge associated with offshore wind is optimal routing and installation of the subsea power cables, which transmit power from the main offshore wind energy production area to a land-based station, where it connects to the electrical grid. By traversing a vast extent of the seafloor, the installation and operational phases of subsea power cables have the potential to result in a range of environmental impacts, which may negatively affect sensitive biological, physical, human and/or cultural resource receptors. Presented here is a case study from southeastern North Carolina to identify optimal seabed cable routes and coastal landfalls for a recently leased offshore wind farm by using a combination of publicly available data, coupled with standard environmental impact assessment methodologies and geographic information system (GIS)-based heat maps. The study identified a range of high-risk areas, in addition to a number of potential low-risk routes and landfall areas which minimize seabed user conflicts and impacts on environmentally sensitive locations. Although additional high-resolution and site-specific environmental, geological and biological surveys are required to develop a robust cable installation plan, the preliminary steps from this research optimize early-phase marine spatial planning for offshore wind projects and other similar subsea industries.

Sound power level and spectrum of port sources for environmental noise mapping

Ports are noisy areas that are often located near populated centers, leading to disturbances for citizens. Neglecting these issues can result in health problems and committees that can impede the natural development of port economic activity, which is growing rapidly. Attention to the sector has increased in recent years, but mainly with studies devoted to the general impact on the population. There is currently insufficient information available regarding the inputs required to conduct noise mapping and assess its effects. This is due to the high quantity and diversity of sources present in the port area. Basing on measurements conducted following established and standardized procedures, the present work reports a database of sound power levels, third-octave band spectra, average duration, and source height for various types of equipment, including reach stackers, dock tractors, front lifts, forklifts, transtainers on wheels, container cranes, mobile cranes, and dry load handling scrapers, during their movements and cargo handling activities. Acousticians are expected to benefit from this detailed input data for noise mapping and environmental acoustic impact assessments.

Comprehensive Performance Evaluation between Visual SLAM and LiDAR SLAM for Mobile Robots: Theories and Experiments

SLAM (Simultaneous Localization and Mapping), primarily relying on camera or LiDAR (Light Detection and Ranging) sensors, plays a crucial role in robotics for localization and environmental reconstruction. This paper assesses the performance of two leading methods, namely ORB-SLAM3 and SC-LeGO-LOAM, focusing on localization and mapping in both indoor and outdoor environments. The evaluation employs artificial and cost-effective datasets incorporating data from a 3D LiDAR and an RGB-D (color and depth) camera. A practical approach is introduced for calculating ground-truth trajectories and during benchmarking, reconstruction maps based on ground truth are established. To assess the performance, ATE and RPE are utilized to evaluate the accuracy of localization; standard deviation is employed to compare the stability during the localization process for different methods. While both algorithms exhibit satisfactory positioning accuracy, their performance is suboptimal in scenarios with inadequate textures. Furthermore, 3D reconstruction maps established by the two approaches are also provided for direct observation of their differences and the limitations encountered during map construction. Moreover, the research includes a comprehensive comparison of computational performance metrics, encompassing Central Processing Unit (CPU) utilization, memory usage, and an in-depth analysis. This evaluation revealed that Visual SLAM requires more CPU resources than LiDAR SLAM, primarily due to additional data storage requirements, emphasizing the impact of environmental factors on resource requirements. In conclusion, LiDAR SLAM is more suitable for the outdoors due to its comprehensive nature, while Visual SLAM excels indoors, compensating for sparse aspects in LiDAR SLAM. To facilitate further research, a technical guide was also provided for the researchers in related fields.

An indigenous geographic position on producing data in colonial conditions

AbstractIn a historically colonial field, what are the possibilities of a geography informed by Indigenous and Anti‐Colonial ethics and onto‐epistemologies? This article suggests engaging in a critical study of data from an Indigenous geographic standpoint, with a focus on imperialism and colonialism in settler nation‐states. I begin by emphasizing the pervasive and long‐standing imposition of geographical data collection in Indigenous life, naming the binds of engaging with the production of data for and with colonial institutions. I then review prominent spatial analytics within critical Indigenous studies, Indigenous geography, and aligned Anti‐Colonial geography, including Indigenous place‐based knowledge and onto‐epistemologies, (racialized) colonial dispossession, sovereignty and recognition, environmental colonialism, and mapping and cartography. Last, I suggest that studies of colonial data dynamics and Indigenous data production strengthen Indigenous and Anti‐Colonial geographies by emphasizing the co‐constitution of good relations and good data. Future research avenues include the need to push beyond the geo‐historical bounds of the category settler colonial, and to build co‐rejections of racial empire with other fields of study including Black, Queer, and Feminist geographies.

Autonomous Exploration Method for Fast Unknown Environment Mapping by Using UAV Equipped With Limited FOV Sensor

Autonomous exploration is crucial and highly challenging for various intelligent operations of unmanned aerial vehicles (UAVs). However, low-efficiency problems caused by low-quality trajectory or back-and-forth maneuvers (BFM) still exist. To improve the exploration efficiency in unknown environments, a fast autonomous exploration planner (FAEP) is proposed in this paper. We firstly design a novel frontiers exploration sequence generation method to significantly reduce BFM during the exploration by considering multi-level factors in asymmetric traveling salesman problem (ATSP). Then, according to the exploration sequence and the distribution of frontiers, an adaptive yaw planning method is proposed to cover more frontiers by yaw change during an exploration journey. In addition, to increase the fluency of flight, a dynamic replanning strategy is also adopted. The main technical contributions of the proposed approach are to provide a comprehensive global coverage path with less BFM, and use adaptive yaw planning to generate more reasonable yaw trajectory. We present extensive comparison and real-world experiments to validate the effectiveness and correctness of our method. Experimental results show the proposed approach has better performance compared to typical and state-of-the-art methods in these flat scenarios without lots of scattered obstacles. We release our implementation as an open-source package <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$^{1}$</tex-math></inline-formula> for the community.

Physically‐Based Lighting for 3D Generative Models of Cars

AbstractRecent work has demonstrated that Generative Adversarial Networks (GANs) can be trained to generate 3D content from 2D image collections, by synthesizing features for neural radiance field rendering. However, most such solutions generate radiance, with lighting entangled with materials. This results in unrealistic appearance, since lighting cannot be changed and view‐dependent effects such as reflections do not move correctly with the viewpoint. In addition, many methods have difficulty for full, 360° rotations, since they are often designed for mainly front‐facing scenes such as faces. We introduce a new 3D GAN framework that addresses these shortcomings, allowing multi‐view coherent 360° viewing and at the same time relighting for objects with shiny reflections, which we exemplify using a car dataset. The success of our solution stems from three main contributions. First, we estimate initial camera poses for a dataset of car images, and then learn to refine the distribution of camera parameters while training the GAN. Second, we propose an efficient Image‐Based Lighting model, that we use in a 3D GAN to generate disentangled reflectance, as opposed to the radiance synthesized in most previous work. The material is used for physically‐based rendering with a dataset of environment maps. Third, we improve the 3D GAN architecture compared to previous work and design a careful training strategy that allows effective disentanglement. Our model is the first that generate a variety of 3D cars that are multi‐view consistent and that can be relit interactively with any environment map.

Artificial Neural Networks for Mapping Coastal Lagoon of Chilika Lake, India, Using Earth Observation Data

This study presents the environmental mapping of the Chilika Lake coastal lagoon, India, using satellite images Landsat 8-9 OLI/TIRS processed using machine learning (ML) methods. The largest brackish water coastal lagoon in Asia, Chilika Lake, is a wetland of international importance included in the Ramsar site due to its rich biodiversity, productivity, and precious habitat for migrating birds and rare species. The vulnerable ecosystems of the Chilika Lagoon are subject to climate effects (monsoon effects) and anthropogenic activities (overexploitation through fishing and pollution by microplastics). Such environmental pressure results in the eutrophication of the lake, coastal erosion, fluctuations in size, and changes in land cover types in the surrounding landscapes. The habitat monitoring of the coastal lagoons is complex and difficult to implement with conventional Geographic Information System (GIS) methods. In particular, landscape variability, patch fragmentation, and landscape dynamics play a crucial role in environmental dynamics along the eastern coasts of the Bay of Bengal, which is strongly affected by the Indian monsoon system, which controls the precipitation pattern and ecosystem structure. To improve methods of environmental monitoring of coastal areas, this study employs the methods of ML and Artificial Neural Networks (ANNs), which present a powerful tool for computer vision, image classification, and analysis of Earth Observation (EO) data. Multispectral satellite data were processed by several ML image classification methods, including Random Forest (RF), Support Vector Machine (SVM), and the ANN-based MultiLayer Perceptron (MLP) Classifier. The results are compared and discussed. The ANN-based approach outperformed the other methods in terms of accuracy and precision of mapping. Ten land cover classes around the Chilika coastal lagoon were identified via spatio-temporal variations in land cover types from 2019 until 2024. This study provides ML-based maps implemented using Geographic Resources Analysis Support System (GRASS) GIS image analysis software and aims to support ML-based mapping approach of environmental processes over the Chilika Lake coastal lagoon, India.

A comprehensive overview of core modules in visual SLAM framework

Visual Simultaneous Localization and Mapping (VSLAM) technology has become a key technology in autonomous driving and robot navigation. Relying on camera sensors, VSLAM can provide a richer and more precise perception means, and its advancement has accelerated in recent years. However, current review studies are often limited to in-depth analysis of a specific module and lack a comprehensive review of the entire VSLAM framework. The VSLAM system consists of five core components: (1) The camera sensor module is responsible for capturing visual information about the surrounding environment. (2) The front-end module uses image data to roughly estimate the camera’s position and orientation. (3) The back-end module optimizes and processes the pose information estimated by the front-end. (4) The loop detection module is used to correct accumulated errors in the system. (5) The mapping module is responsible for generating environmental maps. This review provides a systematic and comprehensive analysis of the SLAM framework by taking the core components of VSLAM as the entry point. Deep learning brings new development opportunities for VSLAM, but it still needs to solve the problems of data dependence, cost and real-time in practical application. We deeply explore the challenges of combining VSLAM with deep learning and feasible solutions. This review provides a valuable reference for the development of VSLAM. This will help push VSLAM technology to become smarter and more efficient. Thus, it can better meet the needs of future intelligent autonomous systems in multiple fields.

INTEGRATION OF STUMPF'S RATIO MODEL AND RANDOM FOREST FOR SATELLITE-DERIVED BATHYMETRY ESTIMATION

Abstract. The development of remote sensing for coastal and marine environment mapping has significantly enhanced our understanding of these ecosystems, enabling improved mitigation strategies against the impacts of human activities. However, remote sensing must consider the complex interplay of the atmosphere and water column. Ongoing research focuses on refining water column correction techniques, including Depth Invariant Indices (DII), Radiative Transfer models, and bathymetry models. This study specifically aims to enhance the Stumpf's Ratio model (SRM) for bathymetry by employing the Random Forest (RF) machine learning regression algorithm. The resulting bathymetry model, which incorporates visible bands from a Sentinel-2 MSI image, and their Stumpf's ratios, outperforms other methods, yielding the highest accuracy with RMSE and R2 values of 1.25 m and 0.854, respectively. This was followed by the multivariate SRM with RMSE and R2 values of 2.196 m and 0.554 respectively These findings demonstrate the promising potential of using RF machine learning regression with SRM for bathymetry modelling.