Land Cover Types Research Articles

Land use and land cover change in locally supported wildlife management areas in the Nyerere-Selous ecosystem, Tanzania

ABSTRACT Worldwide, there is conversion of natural habitats to other land cover types. These are explained by changes in land use and climate change. In Tanzania, environmental degradation happens also within and around protected areas. To mitigate the effects, wildlife management areas (WMAs) surrounding the borders of protected areas in Tanzania have been promoted. They are based on the concept of community based natural resources management (CBNRM). These WMAs have attracted adverse attention because there is a lack of active local participation and of equitable benefits for local people. Unsustainable activities have been reported in these areas. To determine the extent of these activities in WMAs in the Nyerere-Selous ecosystem in Southeastern Tanzania, the researchers did a change detection analysis using Landsat images. Analysis showed that the conditions of the vegetation within WMAs were considerably improving. Although almost all other categories of land use/cover had increased, socio-economic activities had decreased by 25% since the establishment of WMAs in 2003. This decrease is a positive sign towards attaining the goals of CBNRM.

Utilization of Unmanned Aerial Vehicle (UAV) Technology to Identify Land Cover in Kedai Damar Village, Serdang Bedagai, North Sumatera

Remote sensing has been widely used in various fields, one of which is to provide information related to land cover classification Kedai Damar Village is one of 13 villages in the Tebing Tinggi sub-district, Serdang Bedagai Regency. The settlement of Kedai Damar is the one that is most remote from the headquarters of the high cliffs sub-district. This settlement is situated in the center of the PT.Perkebunan Nusantara-IV plantation region in Pabatu North Sumatera. As a result, several rural towns have opened shops providing food and other essentials to farmers and farmworkers in order to rely on PT. Perkebunan Nusantara-IV plantation. This research was conducted in the Kedai Damar Village administrative center area using unmanned aircraft technology and then visually interpretation of aerial photos and mapping administrative area land cover in the Kedai Damar Village administrative center area using processed data in the form of orthophoto from agisoft metashape software. Based on the results of the study, the Kedai Damar Village area has 5 types of land cover classifications that can be identified visually based on 9 elements of interpretation (hue, color, shape, size, texture, pattern, shadow, site and association) as well as ground checks or data collection and observations. In the field. there are 5 types of land cover that can be visually identified, including non-oil Palm, open land, factory Area, settlement, oil palm plantations.

Machine Learning for Urban Heat Island (UHI) Analysis: Predicting Land Surface Temperature (LST) in Urban Environments

This study investigates how urban configuration influences the distribution of heat, known as the Urban Heat Island (UHI) effect, in Shiraz, Iran. Several Machine Learning algorithms are employed to analyze Land Surface Temperature (LST) data across various land cover types, including built-up, soil, and vegetation. The analysis reveals that Deep Neural Networks (DNNs) and Extreme Gradient Boosting (XGB) models excel at predicting LST, outperforming other methods. These results highlight the significant impact of land use on LST patterns within the metropolitan regions. Furthermore, the study assesses the influence of specific configuration metrics within each land cover category. This allows researchers to pinpoint which urban morphology features most significantly affect LST. These insights can inform targeted interventions and management strategies implemented to mitigate heat and improve thermal comfort in specific areas of Shiraz.

Flower-bee versus pollen-bee metanetworks in fragmented landscapes.

Understanding the organization of mutualistic networks at multiple spatial scales is key to ensure biological conservation and functionality in human-modified ecosystems. Yet, how changing habitat and landscape features affect pollen-bee interaction networks is still poorly understood. Here, we analysed how bee-flower visitation and bee-pollen-transport interactions respond to habitat fragmentation at the local network and regional metanetwork scales, combining data from 29 fragments of calcareous grasslands, an endangered biodiversity hotspot in central Europe. We found that only 37% of the total unique pairwise species interactions occurred in both pollen-transport and flower visitation networks, whereas 28% and 35% were exclusive to pollen-transport and flower visitation networks, respectively. At local level, network specialization was higher in pollen-transport networks, and was negatively related to the diversity of land cover types in both network types. At metanetwork level, pollen transport data revealed that the proportion of single-fragment interactions increased with landscape diversity. Our results show that the specialization of calcareous grasslands' plant-pollinator networks decreases with landscape diversity, but network specialization is underestimated when only based on flower visitation information. Pollen transport data, more than flower visitation, and multi-scale analyses of metanetworks are fundamental for understanding plant-pollinator interactions in human-dominated landscapes.

Testing effectiveness in nature reserve management using GIS-based tools: a 25 years monitoring of land use change in a Mediterranean coastal wetland

Land-cover change dynamics were investigated in a Mediterranean coastal wetland to evaluate the long-term effectiveness of nature reserve management. A multitemporal analysis of land cover maps was conducted, utilizing visual interpretation of aerial orthophotos from the summer seasons of 1996, 2008, 2015, and 2021. Landscape changes were evaluated by transition matrices and chord diagrams. Maps were classified in accordance with CORINE land cover types at a fourth level of detail. The multitemporal analyses provided a comprehensive overview of landscape changes within the reserve over the past 25 years. The most notable changes were the increase of wetland areas and the reduction of agricultural and artificial areas. Moreover, seminatural vegetation constantly extended over time. These changes reflected the continuous management activities within the nature reserve, encompassing agreements for water supply, restoration projects, and measures to counteract illegality. These operational actions induced fine-grained ecological changes (outcomes at ecosystem level). This study highlighted the importance of remote sensing and landscape analysis, matched with fine-grained management data, as tool for long-term monitoring. Such an approach provides valuable support in evaluating the effectiveness of strategies promoted in nature reserves hosting wet coastal ecosystems of high conservation concern.

An experimental comparison of pixel-based and object-based classifications with different machine learning algorithms in landscape pattern analysis – Case study from Quang Ngai city, Vietnam

In landscape pattern analysis, the choice of an efficient method for image classification is widely studied, but the features are mostly extracted from digital values by the traditional approach (Pixel-based) and modern approach (Object-based). In this study, we compared the performance of two supervised classification algorithms (Maximum likelihood classifier - MLC and Support vector machines - SVM). We used SPOT-5 image data from 2011 to analyze the landscape pattern of a complex territory in Quang Ngai City, Vietnam. We collected 215 ground-truth samples and classified them into seven landscape classes. The results showed that the overall accuracy of the classification of Pixel-based (MLC), Object-based (MLC), Pixel-based (SVM) and Object-based (SVM) was 67.9%, 74.0%, 72.1%, and 82.3%, respectively. The combination of the object-based approach and SVM algorithm had the best classification result, which reflected the current spatial distribution of land cover types accurately. In the next step, we computed landscape metrics from detailed images to compare quantitative parameters with the actual verification data sources. From these metrics results, we discussed how classification methods could affect landscape structure, and possible ways to improve the accuracy of landscape-pattern identification.

Spatiotemporal analysis of shoreline change trends and adaptation in Bali Province, Indonesia

Shoreline change is a dynamic and complex phenomenon influenced by various natural and anthropogenic factors. Monitoring these changes is crucial for understanding coastal dynamics, managing resources, and mitigating the impacts of coastal erosion and accretion. Remote sensing plays a vital role in monitoring shoreline change. This technology has emerged as a powerful tool for accessing and monitoring shoreline changes due to its ability to capture large-scale spatial data over different periods. This study investigated the dynamic changes in shoreline position in Bali Province from 2016 to 2021 using high-resolution PlanetScope imagery data. Multitemporal shorelines were extracted using the Normalized Difference Water Index (NDWI) to delineate seawater from distinct land-cover types. The end point rate (EPR) model was then used to statistically quantify the shoreline change rates. The results revealed variations in the positions of the shorelines throughout the study, with rapid erosion emerging as a major concern in Bali Province, primarily driven by human activities and/or coastal hydrodynamics. During the study period, the shoreline in Bali Province decreased from 668.64 km to 662.59 km at an average rate of -1.21 m/yr due to continuous erosion, with the most significant retreat occurring at Klungkung Regency. On the other hand, human-caused shoreline advancement, such as land reclamation, harbor, and airport construction, has resulted in a net land increase of 1.25 km2. The protection strategies include structural interventions such as breakwaters and seawalls. The finding provides valuable information that will be helpful for coastal planning and management to reduce the loss of the economy and safeguard the future coastal environment in Bali’s coastal areas.

Land Cover and Land Surface Temperature in the West Bank, Palestine

The 10 major cities in the West Bank (WB), Palestine—Nablus, Ramallah and Al-Bireh, Jenin, Qalqilia, Salfit, Tubas, Jericho, Bethlehem, Tulkarem, and Hebron—are experiencing rapid urban transformation and changing land cover. This study explores the relationship between land cover (built-up and unbuilt areas) and soil type in these cities across benchmark years 1995, 2000, 2005, 2010, 2015, and 2021. In addition to the former, the paper argues that the expansion and increase of the built-up area and the change in soil type of the aforementioned cities in the West Bank, Palestine, are leading to changes in the land surface temperature (LST). This conclusion was reached through a methodological framework that was developed to measure the relationship between the changing land cover (built-up and unbuilt-up areas), soil type, and LST in the 10 major cities in the region. The framework relies on data retrieved through remote sensing in the years from 1995 to 2021. The results of the analysis conducted through this methodological framework showed that there is an inverse relationship between the increase in built-up areas and LST; however, LST is less inside the built-up areas than in the surrounding areas (open spaces) due to different land cover (unbuilt area with grass and shrubs) and different soil type.

Reforestation Will Lead to a Long-Term Downward Trend in the Water Content of the Surface Soil in a Semi-Arid Region

The spatial distribution of soil moisture is a critical determinant for the success of vegetation restoration initiatives in semi-arid and arid regions. The Qilian Mountains, situated within a semi-arid zone in China, have been subject to significant water-induced soil erosion, which has led to extensive restoration activities, predominantly utilizing the species P. crassifolia. However, the interconnections between soil moisture and various land cover types within this region remain unclear, presenting challenges to effective woodland rehabilitation. This study examines the surface soil moisture dynamics in afforested areas with varying ages of plantation to determine the influence of tree planting on the moisture content of the upper soil layer. It investigates the characteristics and temporal patterns of surface soil moisture as the age of the plantation increases. The findings indicate that: (1) soil moisture levels follow a descending sequence from natural forest, through shrubland and grassland, to planted forest and mixed forest, with statistically significant differences observed between natural and mixed forests (p < 0.05); (2) young afforested areas (less than 50 years old) have lower soil moisture levels compared to natural forests, shrublands, or grasslands, and the ecohydrological impacts of afforestation become apparent with a temporal delay; and (3) the analysis using Generalized Additive Mixed Models (GAMM) and the application of Kriging interpolation to determine the spatial distribution of soil moisture reveals that in semi-arid and arid regions, several factors have a pronounced a non-linear relationship with the moisture content of the surface soil. These factors include the duration of afforestation, the position on the lower slope, the presence of shade on the slope, and the scale at which the study is conducted. Therefore, a comprehensive understanding of the dynamics of soil water content is essential to prevent the potential failure of artificially established forests due to inadequate soil moisture in their later stages.

How well do the volunteers label land cover types in manual interpretation of remote sensing imagery?

ABSTRACT High-quality samples for training and validation are crucial for land cover classification, especially in some complex scenarios. The reliability, representativeness, and generalizability of the sample set are important for further researches. However, manual interpretation is subjective and prone to errors. Therefore, this study investigated the following questions: (1) How much difference is there in the interpreters’ performance across educational levels? (2) Do the accuracies of human and AI (Artificial Intelligence) improve with increased training and supporting material? (3) How sensitive are the accuracies of land cover types to different supporting material? (4) Does interpretation accuracy change with interpreters’ consistency? The experiment involved 50 interpreters completing five cycles of manual image interpretation. Higher educational background interpreters showed better performance: accuracies pre-training at 52.22% and 58.61%, post-training at 61.13% and 70.21%. Accuracy generally increased with more supporting material. Ultra-high-resolution images and background knowledge contributed the most to accuracy improvement, while the time series of normalized difference vegetation index (NDVI) contributed the least. Group consistency was a reliable indicator of volunteer sample reliability. In the case of limited samples, AI was not as good as manual interpretation. To ensure quality in samples through manual interpretation, we recommend inviting educated volunteers, providing training, preparing effective support material, and filtering based on group consistency.

Assessment and spatialization of vulnerability of Benin coast to sea level rise using composite/blended approach

Climate change, particularly sea level rise, poses significant challenges to global coastal regions, necessitating a profound understanding of their vulnerability for effective mitigation and adaptation strategies. This study focuses on enhancing scientific insight into West African coastal vulnerability, aiming to assist policymakers and coastal managers in developing sustainable coastal zone management strategies. The methodology employed combines Geographic Information System (GIS) and remote sensing techniques with the Coastal Vulnerability Index (CVI) formula. Parameters such as slope, topography, distance to shoreline, population density, accessibility, land cover, and soil and vegetation types are assessed for their contribution to physical and socio-economic changes induced by sea level rise. These parameters undergo weighting using the Analytic Hierarchy Process (AHP). The socio-economic vulnerability is quantified using the Community-Based Risk Screening Tool-Adaptation and Livelihoods (CRiSTAL). The assessment of the Benin coast reveals significant vulnerability, with very high vulnerability (36.69–70.4, indicated by red cells) and high vulnerability (30.84–36.69, indicated by orange cells) observed in all coastal municipalities (Grand-Popo, Ouidah, Abomey-Calavi, Cotonou, Sèmè-Kpodji), encompassing 40 % and 21 % of the study area, respectively. Moderate (25.69–30.84) and low (10.87–25.69) vulnerability areas are situated at higher elevations inland, covering 35 % and 4 % of the total study area, respectively. No areas of very low vulnerability have been identified. This research contributes significantly to coastal management decisions, adaptation strategies, and climate change policies in Benin by advancing scientific understanding of coastal vulnerability and facilitating the development of sustainable strategies.

Overview and Analysis of Ground Subsidence along China’s Urban Subway Network Based on Synthetic Aperture Radar Interferometry

Deformation along a subway rail network is related to the safe operation of the subway and the stability of construction facilities on the surface, making long-term deformation monitoring imperative. Long-term monitoring of surface deformation along the subway network and statistical analysis of the overall deformation situation are lacking in China. Therefore, targeting 35 Chinese cities whose subway mileage exceeds 50 km, we extracted their surface deformation along subway networks between 2018 and 2022, using spaceborne synthetic aperture radar (SAR) interferometry (InSAR) technology and Sentinel-1 satellite data. We verified the results with the continuous global navigation satellite system (GNSS) stations’ data and found that the root mean square error (RMSE) of the InSAR results was 3.75 mm/year. Statistical analysis showed that ground subsidence along the subways was more prominent in Beijing, Tianjin, and other areas in the North China Plain, namely Kunming (which is dominated by karst landforms), as well as Shanghai, Guangzhou, Qingdao, and other coastal cities. In addition, an analysis revealed that the severity of surface subsidence correlated positively with a city’s gross domestic product (GDP) with a Pearson correlation of 0.787, since the higher the GDP, the more frequent the construction and maintenance of subway, and the more commuters there are, which in turn exacerbates the disturbance to the surface. Additionally, the type of land cover also affects the ground deformation. Our findings provide a reference for constructing, operating, and maintaining the urban subway systems in China.

A Hybrid Index for Monitoring Burned Vegetation by Combining Image Texture Features with Vegetation Indices

The detection and monitoring of burned areas is crucial for vegetation recovery, loss assessment, and anomaly analysis. Although vegetation indices (VIs) have been widely used, accurate vegetation detection is challenging due to potential confusion in the spectra of different types of land cover and the interference of shadow effects caused by terrain. In this work, a novel Vegetation Anomaly Spectral Texture Index (VASTI) is proposed, which leverages the merits of both spectral and spatial texture features to identify abnormal pixels for extracting burned vegetation areas. The performance of the VASTI and its components, the Global Environmental Monitoring Index (GEMI), the Enhanced Vegetation Index (EVI), and the texture feature Autocorrelation (AC) were assessed based on a global dataset previously established, which contains 1774 pairs of samples from 10 different sites. The results illustrated that, compared with the GEMI and EVI, the VASTI improved the user’s accuracy (UA), producer’s accuracy (PA), and kappa coefficient across the ten study areas by approximately 5% to 10%. Compared to AC, the VASTI improved the accuracy of abnormal vegetation detection by 13% to 25%. The improvements were mainly caused by the fact that the incorporation of texture features can reduce spectral confusion between pixels. The innovation of the VASTI is that it considers the relationship between anomalous pixels and surrounding pixels by explicitly integrating spatial texture features with traditional spectral features.

Multisource spatiotemporal analysis of cropping patterns on dry upland: A case study in Rubaru Sub-district, Sumenep Regency

Dry upland agriculture is vital for securing food production in several countries. However, the research on evaluating cropping patterns using remote sensing techniques is completely neglected due to several factors such as the availability of clean imagery and the complexity of the landscape. This research primarily focused on the evaluation of data availability from three different satellite imageries: Sentinel-2, Landsat-8, and MODIS. The consistently high data availability demonstrated by Sentinel-2 established its potential as a reliable source for gap-filling analysis in remote sensing studies. Using a classification model, various land cover types were identified with an overall accuracy of 86.4%, indicating the model's efficiency in accurately classifying these areas. This research also analyzed the detailed cropping patterns, revealing seven distinct temporal cultivation patterns of various crops. This period is strategically positioned between the cultivation of maize, which spans an area of 5,943 ha in December, January, and February, suggesting a potential crop rotation system. The rotation indicated that nearly 83.7% of the cultivated land was planted between maize and shallot throughout the year. The study emphasizes the significance of continuous monitoring and adaptive management in agriculture to ensure sustainability and productivity.

Class imbalance: A crucial factor affecting the performance of tea plantations mapping by machine learning

Due to disparities in area among various land cover types, class imbalance has always existed in crop mapping research, posing uncertainties in extracting minority classes which occupy a smaller area. In this paper, taking tea plantations mapping in Hangzhou city as an example, we created a series of training datasets with different imbalance-ratios (IRs), compared the accuracy between the extraction models using these datasets, and analyzed the impact of class imbalance on various machine learning algorithms (Artificial Neural Network, Decision Tree, Random Forest and XGBoost), aiming to provide a feasible approach to improve the mapping accuracy of minority classes. The leave-one-out cross validation results showed that in most cases, with the increase of the IR, the model’s F2-score first increased and then decreased, and the increase of F2-scores ranged from 0.2% to 29.2%, suggesting that moderately increasing the number of other samples in the training dataset can improve the tea plantations extraction accuracy. Consistent result can also be obtained by using the whole city’s samples for modeling and random sampling validation. XGBoost performed best among the four algorithms, which yielded the optimal tea plantations map with a PA of 97%, UA of 93% and F2-score of 96% when the IR of the training dataset was 6. The UA was 19% higher than that of the model using a balanced dataset (IR=1) and was 11% higher than that of the model using pseudo-balanced datasets created by the oversampling method. The conclusions of this study offer insights for the identification of minority classes, contributing to achieving higher accuracy in remote sensing crop mapping.

Description of swine producer biosecurity planning for foreign animal disease preparedness using the Secure Pork Supply framework.

Preventing potential foreign animal diseases is a high priority, with re-emerging threats such as African Swine Fever emerging close to North American borders. The Secure Pork Supply (SPS) plan provides a voluntary framework for swine producer biosecurity planning and disease outbreak preparedness. However, biosecurity knowledge varies greatly among swine veterinarians, managers, and caretakers within the industry, which impacts the understanding, quality, implementation and biosecurity plan agreements with the SPS guidelines unless review procedures and quality control mechanisms are in place. Therefore, this study aimed to describe and identify the level of biosecurity planning agreements between producer-and/or swine veterinarian-made biosecurity plans for commercial swine sites and the SPS plan guidelines during a review process. Biosecurity maps (N = 368) and written plans (N = 247) were obtained from six Midwest swine companies/veterinary clinics. Maps were evaluated on accuracy and placement of mandatory map features based on SPS guidelines, and discrepancies between the development of producer-made biosecurity maps and written biosecurity plans. Multivariable mixed logistic regression analyses were conducted to identify differences in SPS planning accuracy based on herd size, production stage, and characteristics related to geographical site location (e.g., land cover type and expected feral swine population density in the region). In this study, 55.8% (205/368) of all provided biosecurity maps had to be revised due to misplaced or missing map features. In addition, 80.9% (200/247) of the written plans had one or more conflicts with the corresponding biosecurity maps. The main biosecurity planning issues involved feed delivery activities, where the mapping of vehicle movements (89.9%, 222/247) were in direct conflict with the written SPS plans. Sites located in areas with a moderate expected feral swine population density had 3-fold increased odds of needing map revisions compared to sites with low expected feral swine population density. Sites located in predominately farmland had 7.3% lower odds of having biosecurity map and SPS plan conflicts for every 1.0% increase in farmland landcover in a 10-km radius around the swine site. Human oversight or lack of knowledge regarding biosecurity planning and implementation is common, which may culminate in important preparedness shortcomings in disease prevention and control strategies for U.S. swine farms. Future efforts should focus on additional biosecurity training for swine producers and veterinarians alongside with quality control benchmarking of producer made plans.

BLEI: Research on a Novel Remote Sensing Bare Land Extraction Index

Bare land, as a significant land cover type on the Earth’s surface, plays a crucial role in supporting land-use planning, urban management, and ecological environmental research through the investigation of its spatial distribution. However, due to the diversity of land-cover types on the Earth’s surface and the spectral complexity exhibited by bare land under the influence of environmental factors, it is prone to confusion with urban and other land features. In order to extract bare land rapidly and efficiently, this study introduces a novel bare land extraction index called the Bare Land Extraction Index (BLEI). Then, considering both Ganzi Tibetan Autonomous Prefecture and Urumqi, China as the study areas, we compared BLEI with three presented indices: the Bare-soil Index (BI), Dry Bare Soil Index (DBSI), and Bare Soil Index (BSI). The results show that BLEI exhibits excellent efficacy in distinguishing bare land and urban areas. It gets the most outstanding accuracy in bare land identification and mapping, with overall accuracy (OA), kappa coefficient, and F1-score of 98.91%, 0.97, and 97.89%, respectively. Furthermore, BLEI is also effective in distinguishing bare land from sandy soil, which can not only improve the mapping accuracy of bare land in soil-deserted areas but also provide technological support for soil research and land-use planning.

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.

ANALYSIS OF NOVASAR-1 S-BAND DATA IN DEVELOPING AN ALTERNATIVE LAND COVER MAPPING

Abstract. The Advanced Science and Technology Institute of the Department of Science and Technology (DOST-ASTI), through its Synthetic Aperture Radar and Automatic Identification System (SARwAIS) Project, has gained access to S-Band SAR images acquired by the NovaSAR-1 satellite of UK’s Surrey Satellite Technology Ltd. (SSTL) To help maximize the utility of these images especially in the aspect of terrain-related applications, their viability as potential alternatives to datasets like optical satellite images and other SAR images in characterizing land cover types was evaluated. Statistical analyses on the backscatter values from the tri-polarization ScanSAR datasets using Multivariate Analysis of Variance (MANOVA) and its corresponding post-hoc tests showed that there is a significant difference on the mean backscatter values at 0.05 level of significance. Moreover, Tukey’s honestly significant difference (Tukey’s HSD) test determined which pairs contribute to the significant difference. Using the Random Forest algorithm resulted in an accuracy of 66.93% without further optimization and/or reduction in the number of land covers being classified. Despite the relatively unremarkable accuracy score, it still showed potential for data augmentation with optical satellites for land cover mapping and other terrain-related applications.

ENHANCEMENT OF THE FIELD ASSESSMENT PROTOCOLS AND SUITABILITY MAPS FOR COCONUT

Abstract. The crop suitability assessment particularly in coconut planting has not been revisited in over two decades. An in-depth analysis of the various factors affecting coconut farming was conducted. This involved the utilization of local remotely-sensed data on elevation, slope, soil type, and land cover. Global gridded data on rainfall and land surface temperature were acquired to supplement the local data. Each factor was given its corresponding weight assignments upon consultation with the experts from the Philippine Coconut Authority. Variable factors such as rainfall (15%) and temperature (10%) were given with lower scores than the permanent or nearly unchanging factors on elevation (25%), slope (25%), and soil type (25%). These individual factors were processed for the final multi-criteria weighted overlay analysis. Finally, the land cover map was used to remove areas deemed unsuitable for coconut planting. Results showed that about 20 million hectares of the country’s total land area are suitable for coconut planting with varying levels of suitability. Of the total suitable areas, only 3.64 million hectares (18%) were planted with coconuts based on the PSA data for 2021. One important factor to consider is that most of the areas not planted with coconut are devoted to other important land cover types like forests, perennials, and annual crops. The utilization of the open source Quantum GIS (QGIS) software proves to be essential in this kind of enormous data processing and analysis, coupled with the generation of very detailed coconut suitability data and maps on a nationwide scale.