Habitat Mapping Research Articles

Using spectral diversity and heterogeneity measures to map habitat mosaics: An example from the Classical Karst

AbstractQuestionsCan we map complex habitat mosaics from remote‐sensing data? In doing this, are measures of spectral heterogeneity useful to improve image classification performance? Which measures are the most important? How can multitemporal data be integrated in a robust framework?LocationClassical Karst (NE Italy).MethodsFirst, a habitat map was produced from field surveys. Then, a collection of 12 monthly Sentinel‐2 images was retrieved. Vegetation and spectral heterogeneity (SH) indices were computed and aggregated in four combinations: (1) monthly layers of vegetation and SH indices; (2) seasonal layers of vegetation and SH indices; (3) yearly layers of SH indices computed across the months; and (4) yearly layers of SH indices computed across the seasons. For each combination, a Random Forest classification was performed, first with the complete set of input layers and then with a subset obtained by recursive feature elimination. Training and validation points were independently extracted from field data.ResultsThe maximum overall accuracy (0.72) was achieved by using seasonally aggregated vegetation and SH indices, after the number of vegetation types was reduced by aggregation from 26 to 11. The use of SH measures significantly increased the overall accuracy of the classification. The spectral β‐diversity was the most important variable in most cases, while the spectral α‐diversity and Rao's Q had a low relative importance, possibly because some habitat patches were small compared to the window used to compute the indices.ConclusionsThe results are promising and suggest that image classification frameworks could benefit from the inclusion of SH measures, rarely included before. Habitat mapping in complex landscapes can thus be improved in a cost‐ and time‐effective way, suitable for monitoring applications.

Forensic Wetland and Deepwater Habitat Mapping for Setting Pre-development Conditions

Mapping wetlands and deepwater habitats prior to modern settlement is difficult due to the difficulty of obtaining sufficient, spatially explicit data on conditions prior to the middle of the 20th century. We overcame this barrier by using Public Land Survey System data and other ancillary historical data to map wetlands and deepwater habitats in the 1850s in the mainland portion of St. Lucie County, Florida. Using just the Public Land Survey System data, a first draft map indicated there was 754 km2 of wetlands and deepwater habitats covering 52% of the study area. After two iterations using other ancillary historical data, a third and final draft map indicated there was 1,222 km2 of wetlands and deepwater habitats covering 84% of the study area, and overall increase of 62%. These results show that PLSS data can be used to map wetlands and deepwater habitats prior to modern settlement, but the use of other ancillary historical data can make maps more accurate and trustworthy. The outcome is a first-of-its-kind map of wetlands and deepwater habitats in the mainland portion of St. Lucie County, which is now representing baseline conditions in ongoing projects seeking to both quantify and mitigate for widespread land use-land cover change.

Monitoring benthic habitats in English Marine Protected Areas: Lessons learned, challenges and future directions

Thousands of Marine Protected Areas (MPAs) have been designated around the globe to conserve benthic habitats, following the adoption of Convention on Biodiversity Aichi Target 11 and widespread endorsement of the ‘30by30’ initiative. When designed and managed effectively, MPAs can enrich biodiversity, enhance ecosystem services and regulate stakeholder access. High quality dedicated monitoring programmes are essential to determine MPA effectiveness at the correct spatial and temporal scales; however, such programmes can be fraught with complexities and many MPAs have not yet implemented them following designation. There is, therefore, a clear need and opportunity for scientists to share and draw on collective experiences to help reduce barriers to successful MPA monitoring. This study synthesises lessons learned and challenges encountered in the English MPA monitoring programme, reflecting on solutions and future directions. Twenty-three MPA monitoring reports were reviewed and the key findings were extracted. The majority were centred around the need to consider monitoring approaches at the scale of each individual MPA, rather than adoption of generic ‘one-size-fits-all’ practices. Various challenges were found to be inherent, whilst some were prioritised for further development: MPA-scale measures of condition, fishing activity data, seabed imagery acquisition and analysis, DNA technologies, habitat mapping, and ecosystem approaches to MPA monitoring. This study highlights the benefits of strong multi-disciplinary partnerships for addressing the complex issues encountered in MPA monitoring programmes. We endorse further studies, technical advancements and a more holistic ecosystem approach to understanding human impacts on the benthos, thus optimising MPA management and positive conservation outcomes.

Benthic habitat mapping and assessment of seagrass species diversity in Da Lon Reef, Truong Sa Islands, Vietnam, using very high-resolution satellite imagery and in situ data

Benthic habitats are critical in shallow sea areas; they regulate the diversity and richness of organisms in each area. Mapping benthic habitats elucidates natural sea characteristics and aids in managing and using natural resources, as well as conserving marine biodiversity. This study established a benthic habitat map for the Da Lon Reef area, Truong Sa Islands, Vietnam, using Pléiades high-resolution remote sensing imaging materials and field survey results from 2020 and 2021. We identified seven classes of benthic habitats with a 91.64% overall accuracy, corresponding to a Kappa coefficient of 0.88. In the Da Lon Reef, seagrass biomes occupy a large area (more than 200 ha) and are distributed mainly inside lagoons at depths of 2–6 m. The field survey results identified five seagrass species and the biodiversity and biomass of seagrass populations in the lagoon of Da Lon Reef. The study results confirm the fundamental value of resources, biodiversity in general and seagrass in particular, in managing and protecting shallow sea ecosystems and biodiversity conservation in the Da Lon Reef area, an important part of the Truong Sa Islands, Vietnam.

Cost and quality of operational larviciding using drones and smartphone technology

BackgroundLarval Source Management (LSM) is an important tool for malaria vector control and is recommended by WHO as a supplementary vector control measure. LSM has contributed in many successful attempts to eliminate the disease across the Globe. However, this approach is typically labour-intensive, largely due to the difficulties in locating and mapping potential malarial mosquito breeding sites. Previous studies have demonstrated the potential for drone imaging technology to map malaria vector breeding sites. However, key questions remain unanswered related to the use and cost of this technology within operational vector control.MethodsUsing Zanzibar (United Republic of Tanzania) as a demonstration site, a protocol was collaboratively designed that employs drones and smartphones for supporting operational LSM, termed the Spatial Intelligence System (SIS). SIS was evaluated over a four-month LSM programme by comparing key mapping accuracy indicators and relative costs (both mapping costs and intervention costs) against conventional ground-based methods. Additionally, malaria case incidence was compared between the SIS and conventional study areas, including an estimation of the incremental cost-effectiveness of switching from conventional to SIS larviciding.ResultsThe results demonstrate that the SIS approach is significantly more accurate than a conventional approach for mapping potential breeding sites: mean % correct per site: SIS = 60% (95% CI 32–88%, p = 0.02), conventional = 18% (95% CI − 3–39%). Whilst SIS cost more in the start-up phase, overall annualized costs were similar to the conventional approach, with a simulated cost per person protected per year of $3.69 ($0.32 to $15.12) for conventional and $3.94 ($0.342 to $16.27) for SIS larviciding. The main economic benefits were reduced labour costs associated with SIS in the pre-intervention baseline mapping of habitats. There was no difference in malaria case incidence between the three arms. Cost effectiveness analysis showed that SIS is likely to provide similar health benefits at similar costs compared to the conventional arm.ConclusionsThe use of drones and smartphones provides an improved means of mapping breeding sites for use in operational LSM. Furthermore, deploying this technology does not appear to be more costly than a conventional ground-based approach and, as such, may represent an important tool for Malaria Control Programmes that plan to implement LSM.

Coral reef applications of Landsat-8: geomorphic zonation and benthic habitat mapping of Xisha Islands, China

ABSTRACT Being one of the most significant and valuable coral reef systems in the South China Sea, the Xisha Islands has undergone rapid transformation due to increasing stressors from human impacts and climate change in recent years. However, as indispensable information for coral reef monitoring and management, the detailed reef extent, geomorphic zonation, or benthic composition of the Xisha Islands is not well documented. Considering limited access to the Xisha Islands, the rapid development of optical remote sensing technology provides us with a feasible mean for coral reef observation. This study adopted a water depth substitution index – probabilistic inundation (PI) – combined with depth-invariant index (DII) to achieve reef extent exploration, geomorphologic and benthic habitat types classification with unsupervised classification algorithms based on Landsat-8 time-series satellite data. Compared with two open-access datasets, the extent of each independent reef extracted from PI exhibited higher similarity with the actual boundary conditions displayed in RGB (Red-Green-Blue) composite images from Landsat-8. Based on PI and derived slope, we obtained geomorphic zonation classification results, and similarly benthic compositions were retrieved based on PI, DII, and reflectance. The overall accuracy of geomorphic zonation and benthic habitat classification results were 72% and 86%, respectively. We also interestingly discovered that corals of the Xisha Islands may be capable of an ability to resist chronic heat stress as a growth trend of reef area after two successive stress events in 2014–2015 were observed at most reefs. The proposed mapping framework of this study provides a repeatable and flexible scheme in depicting the comprehensive situation of coral reefs at Xisha Islands based only on publicly available remote sensing data without complicated pre-set parameters, which could be easily extended to coral reef research around the world. Simultaneously, the findings also provide requisite information supporting the sustainable management and conservation of coral reef ecosystems in the Xisha Islands.

Seagrass ecosystem biodiversity mapping in part of Rote Island using multi-generation PlanetScope imagery

Remote sensing offers an effective and efficient solution to provide information on the biodiversity of seagrass ecosystems, which is currently lacking in most parts of the world. Therefore, this study aimed to map the biodiversity of seagrass ecosystems in parts of Rote Island, which is one of the seagrass biodiversity hotspots, using multi-generation PlanetScope magery to see how they compare. The most frequently used biodiversity indicators were identified, including the major benthic habitat (coral, seagrass, macroalgae, bare substrate) and the composition of seagrass species based on life forms. We also aim to understand the actual biodiversity indicators of seagrass ecosystems captured by PlanetScope imagery. To achieve this, field data was integrated with the resulting ISODATA classification results to assess what ISODATA class clusters represent in the field, and new classification schemes are developed accordingly. The random forest algorithm was used to carry out the classification, with seagrass field data serving as training data. Independent field data was subsequently used to assess the accuracy. The results showed that the accuracy of benthic habitat and seagrass mapping ranged from 60%-70%. However, through the use of a classification scheme built on ISODATA clustering, the spatial distribution of classes and accuracy of all PlanetScope images was significantly improved to > 90%. This highlighted the importance of understanding which indicators of seagrass biodiversity were effectively captured by PlanetScope images to achieve higher mapping accuracy. Overall, this approach optimized the ability of PlanetScope images to map seagrass biodiversity while obtaining a higher number of biodiversity indicator classes and mapping accuracy than the commonly used biodiversity indicator classification scheme.

Seagrass ecosystem biodiversity mapping in part of Rote Island using multi-generation PlanetScope imagery

Remote sensing offers an effective and efficient solution to provide information on the biodiversity of seagrass ecosystems, which is currently lacking in most parts of the world. Therefore, this study aimed to map the biodiversity of seagrass ecosystems in parts of Rote Island, which is one of the seagrass biodiversity hotspots, using multi-generation PlanetScope magery to see how they compare. The most frequently used biodiversity indicators were identified, including the major benthic habitat (coral, seagrass, macroalgae, bare substrate) and the composition of seagrass species based on life forms. We also aim to understand the actual biodiversity indicators of seagrass ecosystems captured by PlanetScope imagery. To achieve this, field data was integrated with the resulting ISODATA classification results to assess what ISODATA class clusters represent in the field, and new classification schemes are developed accordingly. The random forest algorithm was used to carry out the classification, with seagrass field data serving as training data. Independent field data was subsequently used to assess the accuracy. The results showed that the accuracy of benthic habitat and seagrass mapping ranged from 60%-70%. However, through the use of a classification scheme built on ISODATA clustering, the spatial distribution of classes and accuracy of all PlanetScope images was significantly improved to > 90%. This highlighted the importance of understanding which indicators of seagrass biodiversity were effectively captured by PlanetScope images to achieve higher mapping accuracy. Overall, this approach optimized the ability of PlanetScope images to map seagrass biodiversity while obtaining a higher number of biodiversity indicator classes and mapping accuracy than the commonly used biodiversity indicator classification scheme.

Anchoring pressure and the effectiveness of new management measures quantified using AIS data and a mobile application

Large boats can have a major impact on sensitive marine habitats like seagrass meadows when anchoring. The anchoring preference of large boats and their impacts can be mapped using Automatic Identification System (AIS). We found a constant increase in the number of anchoring events with, until recently, a large part of them within the protected Posidonia oceanica seagrass meadows. French authorities adopted a new regulation in 2019 forbidding any anchoring within P. oceanica seagrass meadows for boats larger than 24 m. The number of large ships (>24 m) anchoring in P. oceanica meadows significantly decreased after the enforcement of the regulation. The surface of avoided impact thanks to the new regulation corresponds to 134 to 217 tons of carbon sequestered by the preserved meadow in 2022. This work illustrates that a strict regulation of anchoring, based on accurate habitat maps, is effective in protecting seagrass meadows.

Comments on Acosta-Velázquez et al. changes in mangrove coverage classification criteria could impact the conservation of mangroves in Mexico. Land Use Policy, 2023, 129, 106651

Accurate and up-to-date mapping of mangrove habitats is crucial for effective conservation and management strategies and policies. As a reply to the comparative assessment realized by Acosta et al. (2023) to the last map produced by the Mexican Mangrove Monitoring System (MMMS) and the conclusions resulting from it, we provide a comprehensive response addressing the concerns raised. We acknowledge that maps are not infallible and are subject to improvement, particularly in the rapidly advancing field of remote sensing technology used in long term monitoring system. The MMMS mapping efforts utilize state-of-the-art remote sensing technologies, such as high-resolution satellite imagery and advanced methodologies, to enhance precision and efficiency. Moreover, MMMS mapping integrates regional external expert knowledge to increase accuracy at uncertain locations. We emphasize the importance of accuracy and reliability in mangrove mapping due to the potential irreversible consequences of mangrove loss. The MMMS provides a valuable tool for monitoring deforestation rates, understanding spatial distribution, supporting management decisions, identifying conservation priorities, and facilitating targeted conservation actions. We highlight the application of the precautionary principle as an environmental imperative for the Mexican government. The inclusion of previously classified "Other wetlands" as mangroves in the MMMS mapping system implies the acknowledgment of their integral role in supporting biodiversity and climate change mitigation efforts. Technological progress and collaborative efforts have made this reclassification possible, enhancing our understanding and expertise in distinguishing mangroves from other wetland types. We conclude that our mapping efforts align with the objective of attaining high classification accuracy in remote sensing, and we remain committed to continuous improvement in our mangrove mapping endeavors.

Finding Misclassified Natura 2000 Habitats by Applying Outlier Detection to Sentinel-1 and Sentinel-2 Data

The monitoring of Natura 2000 habitats (Habitat Directive 92/43/EEC) is a key activity ensuring the sufficient protection of European biodiversity. Reporting on the status of Natura 2000 habitats is required every 6 years. Although field mapping is still an indispensable source of data on the status of Natura 2000 habitats, and very good field-based data exist in some countries, keeping the field-based habitat maps up to date can be an issue. Remote sensing techniques represent an excellent alternative. Here, we present a new method for detecting habitats that were likely misclassified during the field mapping or that have changed since then. The method identifies the possible habitat mapping errors as the so-called “attribute outliers”, i.e., outlying observations in the feature space of all relevant (spectral and other) characteristics of an individual habitat patch. We used the Czech Natura 2000 Habitat Layer as field-based habitat data. To prepare the feature space of habitat characteristics, we used a fusion of Sentinel-1 and Sentinel-2 satellite data along with a Digital Elevation Model. We compared outlier ratings using the robust Mahalanobis distance and Local Outlier Factor using three different thresholds (Tukey rule, histogram-based Scott’s rule, and 95% quantiles in χ2 distribution). The Mahalanobis distance thresholded by the 95% χ2 quantile achieved the best results, and, because of its high specificity, appeared as a promising tool for identifying erroneously mapped or changed habitats. The presented method can, therefore, be used as a guide to target field updates of Natura 2000 habitat maps or for other habitat/land cover mapping activities where the detection of misclassifications or changes is needed.

An agent-based model to quantify energetics, movement and habitat selection of mid-continent mallards in the Mississippi Alluvial Valley

The dynamics of wintering waterfowl populations at the landscape scale are the result of complex interactions of environmental, behavioral and energetic drivers. Agent-based models provide a method to directly link these factors in a spatially explicit framework and allow the emergence of patterns from the aggregation of individual agent actions. We adapted the Spatially-explicit Waterbird Agent-based Model Program (SWAMP), originally developed for waterfowl in central California, to simulate a basin-scale population of mallards (A. platyrhynchos) wintering in the Mississippi Alluvial Valley over a four-month period (November–February). Simulated agents move within the landscape, foraging on areas made available based on a probabilistic inundation status, and converting food resources to endogenous energy. The model uses a high-resolution map of eastern Arkansas waterfowl habitats and incorporates a hierarchical habitat selection system that enables mallards to relocate at increasing scales in response to changing food availability. We validated the performance of modeled mallard body condition and behavioral metrics under a range of environmental conditions against expected outcomes derived from empirical data and found that the simulation produced realistic representations of changes in flight distances, energy expenditure, lipid storage, and foraging habitat use in response to depleting food resources over time. We discuss the model's applicability as a tool to quantify waterfowl response to a range of environmental conditions and to evaluate scenarios of landscape composition and configuration in the context of waterfowl population management.

Marine Habitat Mapping using Multibeam Echosounder Survey and Underwater Video Observations: A Case Study from Tioman Marine Park

In recent years, there has been an increasing trend of utilizing high-resolution multibeam echosounder (MBES) datasets and supervised classification via machine learning to create marine habitat maps. The purpose of current study was threefold: (1) to extract bathymetric and backscatter derivatives from a multibeam dataset, (2) to measure the correlation between bathymetric and backscatter derivatives, and (3) to generate a marine habitat map using the Random Forest (RF). Tioman Marine Park (TMP), which is situated Southeast China Sea. MBES surveyed area are encompassed an area of 406 km² and served as the location for the study. Based on results and analysis, fourteen (14) derivative were derived from bathymetry map and backscatter mosaic. The second step involved integrating variables and a total of 152 of habitat ground-truth data were used, derived from underwater imageries, and sediment samples, into an RF model to generate a map of the marine habitat. Based on marine habitat map, six habitat classes including sand, rock, gravel and sand, coral rubble, coral and rock, and coral were classified. The distribution of coral habitat was found to be correlated with the depth of the bathymetry in the shallow water region. Therefore, the study has reached the conclusion that the integration between MBES derivatives, ground-truth data, and RF machine learning algorithm is an effective in classifying the distribution of marine habitats, specifically the coral habitat.

ROCK ARMOUR: A BENTHIC HABITAT PROVIDING VALUABLE ECOSYSTEM SERVICES IN THE CARIBBEAN SEA

This paper describes our findings from ecological surveys at several shoreline and beach enhancement projects in the Caribbean. Using standard fish abundance and diversity surveys and benthic habitat mapping protocols, we track how rock armour transitions from a barren substrate at installation to a diverse marine ecosystem over time. The ecosystem services provided by the rock armour have been evaluated and compare well with naturally occurring habitats. Using available economic benefit analyses, we estimate the value of these ecosystem services at various stages as the rock armour habitat matures.

DORSL-FIN: A Self-supervised Neural Network for Recovering Missing Bathymetry from ICESat-2

Bathymetric data, comprising elevations of submerged surfaces (e. g., seafloor or lake bed), constitute a critical need for a wide range of science and application focus areas, such as safety of marine navi- gation, benthic habitat mapping, flood inundation modeling, and coastal engineering. Over the past decade, the availability of near- shore bathymetric data has increased dramatically due to advances in satellite-derived bathymetry (SDB). One notable advance occurred with the 2018 launch of NASA's Ice, Cloud, and land Elevation Satellite 2 (ICESat-2), carrying the Advanced Topographic Laser Altimeter System (ATLAS). However, much like other Earth observing satellites, ATLAS is often hampered by obstructions, such as clouds, which block the sensor's view of the Earth's surface. In this study, we introduce the Deep Occlusion Recovery of Satellite Lidar From ICESat-2 Network (DORSL-FIN) to recover partially occluded bathymetric profiles. We show that DORSL-FIN is able to accurately recover occluded bathymetry and outperforms other methods of interpolation.

New and poorly known species of Palpimanus Dufour, 1820 (Araneae, Palpimanidae) from Uzbekistan and Tajikistan

Two new species, Palpimanus logunovi sp. n. (♂♀) and P. rakhimovi sp. n. (♂♀), are described from Tajikistan and Uzbekistan respectively. Lectotype has been designated for the poorly known species, P. sogdianus Charitonov, 1946 from Uzbekistan and is redescribed based on type and newly collected material. (Re)descriptions, figures, diagnoses, distribution map and photograps of habitats of all the studied species are provided.

Mapping Seagrass Biodiversity Indicators of Pari Island using Multiple WorldView-2 Bands Derivatives

Comprehensive information on seagrass biodiversity indicators, such as species composition, percentage cover, and biomass carbon stock, remains limited across various regions globally. Mapping these indicators using remote sensing images requires extracting maximum information from the input images to achieve effective results. This study aims to map seagrass distribution, percent cover (PC), and aboveground carbon stock (AGC) as biodiversity indicators in the optically shallow waters surrounding Pari Island. We integrate WorldView-2 (WV2) derivatives, field seagrass data, and RF classification and regression algorithms to accomplish this objective. The WV2 image derivatives encompass surface reflectance bands, band ratios, mean and variance co-occurrence texture bands, and principle component bands. These inputs are used individually and collectively for mapping, employing a random forest algorithm trained with field seagrass data. Our results demonstrate that the most accurate benthic habitat map achieves an overall accuracy (OA) of 65.2%, with a user's accuracy of 65.2% and a producer's accuracy of 72.8% for the seagrass-dominated class. Seagrass PC mapping yields a root mean square error (RMSE) of 17.1%, with an average PC of 47.4 ± 9.9%. Seagrass AGC mapping achieves an RMSE of 5.0 g C m-2, with an average AGC range of 6.2 – 29.1 g C m-2, estimating the study area's aboveground biomass carbon stock at 27.9 tons C. Combined inputs produce the most accurate results for all biodiversity indicators, emphasizing the importance of utilizing combined bands from SR band derivatives to maximize information input for training mapping algorithms, instead of using derivative bands individually or as replacements for the initial SR bands.
 Keywords : Seagrass; Biodiversity; Mapping; WorldView-2; Pari Island
 
 Copyright (c) 2023 Geosfera Indonesia and Department of Geography Education, University of Jember
 This work is licensed under a Creative Commons Attribution-Share A like 4.0 International License

Modeling risks in marine protected areas: Mapping of habitats, biodiversity, and cultural ecosystem services in the southernmost atlantic coral reef

Marine Protected Area (MPA) is a fundamental strategy for the maintenance of ocean ecological processes worldwide and, consequently, their associated ecosystem services. Nevertheless, the quality of the services provided by MPAs, including cultural services such as recreational activities, depends on the effective management of marine habitats and biodiversity. Here, we performed an ecosystemic assessment in reef environments within a subtropical MPA, modeling the potential risks for their habitats and their recreational activities. The Queimada Grande Island (QGI), southeastern Brazil, was used as the model area since this island encompasses a unique and irreplaceable marine habitat, the Southernmost Atlantic coral reef. We firstly assessed and mapped the habitats, the biodiversity, and the recreational activities associated with QGI reefs. Next, we considered different scenarios of management for the modeling risks across the study area. We found that the coral reef and its adjacent habitats, such as the rhodolith bed, make the sheltered face of the island an important area for the provision of the cultural ecosystem services and overlapping uses such as onboard recreational fishing, spearfishing, and recreational diving. This area was also evaluated as the one under the highest risk of impact, considering the current scenario of management. The most successful scenario modeling to reduce these risks was the hypothetical implementation of a 66% reduction of all activities over all QGI habitats. Despite that, the scenario simulating the application of the regulations present in the MPA management plan was enough to reduce almost half the maximum risk value. Therefore, we concluded that to provide a balance among conservation, uses, and the local economy, the application of these regulations is the better management scenario modeled for the study area. Such results provided useful information and tools for local management and decision-making in this singular marine environment, also being an example for mapping ecosystem services and modeling risks in MPAs worldwide.

Financial derivative features based integrated potential fishing zone (IPFZ) Future forecast

In India, around 7 million people depend on fishing for their livelihoods. They are assisted with a reliable and fast brief forecast for the areas of fish aggregations. Habitat mapping is critical in supporting strategic choices on fish usage and protection. In conjunction with techniques for machine learning, remote control has made comprehensive fish mapping on relevant scales possible. In machine learning, supervised algorithms are utilized to make forecasts from datasets, when data is accessible without relating output factors. In this research work, Ocean Surface Temperature (OST) and Satellite derived Chlorophyl material are the basic inputs to generating the information of Potential Fishing Zone (PFZ). The 16 features and additional financial derivative features are used for accurate future prediction of PFZ. The unwanted and missing data are removed using effective pre-processing techniques. Among the various methods available for forecasting nonlinear phenomena, the Neural Network is the best and the efficient method to get a forecast. Therefore, the Function Fitting Neural Network (FFNN) technique is mainly used to predicting the Integrated Potential Fishing Zone (IPFZ). The practical analyses are performed by analysing the 80% -20%, 60% -40% and future data in terms of various parameters. From the results, it is proved that the suggested FFNN achieved 90% of accuracy, where the existing neural network achieved 86% of accuracy by implementing with financial derivative features for the 80% -20% of available dataset.

Three-Dimensional Mapping of Habitats Using Remote-Sensing Data and Machine-Learning Algorithms

Progress toward habitat protection goals can effectively be performed using satellite imagery and machine-learning (ML) models at various spatial and temporal scales. In this regard, habitat types and landscape structures can be discriminated against using remote-sensing (RS) datasets. However, most existing research in three-dimensional (3D) habitat mapping primarily relies on same/cross-sensor features like features derived from multibeam Light Detection And Ranging (LiDAR), hydrographic LiDAR, and aerial images, often overlooking the potential benefits of considering multi-sensor data integration. To address this gap, this study introduced a novel approach to creating 3D habitat maps by using high-resolution multispectral images and a LiDAR-derived Digital Surface Model (DSM) coupled with an object-based Random Forest (RF) algorithm. LiDAR-derived products were also used to improve the accuracy of the habitat classification, especially for the habitat classes with similar spectral characteristics but different heights. Two study areas in the United Kingdom (UK) were chosen to explore the accuracy of the developed models. The overall accuracies for the two mentioned study areas were high (91% and 82%), which is indicative of the high potential of the developed RS method for 3D habitat mapping. Overall, it was observed that a combination of high-resolution multispectral imagery and LiDAR data could help the separation of different habitat types and provide reliable 3D information.