Table 7 - uploaded by Chinsu Lin
Content may be subject to copyright.
Source publication
Changes of Land Use and Land Cover (LULC) affect atmospheric, climatic, and biological spheres of the earth. Accurate LULC map offers detail information for resources management and intergovernmental cooperation to debate global warming and biodiversity reduction. This paper examined effects of pansharpening and atmospheric correction on LULC class...
Similar publications
Citations
... NDBI, akin to NDVI, capitalizes on the assessment of light reflectance, although it operates in the shortwave-infrared and mid-infrared (SWIR/NIR) spectral ranges. This metric finds extensive application across various domains, including urban planning and land use studies, to identify built-up areas and impervious surfaces, as well as assess changes in urban landscapes (Lin et al. 2015). NDBI computation follows a similar pattern, involving the subtraction of MIR reflectance from SWIR reflectance and then dividing by their summation. ...
... Accuracy plays a crucial role in assessing the degree to which different image processing techniques align with the imagery (Lin et al. 2015;Zhang et al. 2016). The confusion matrix, as part of a broader accuracy assessment, holds significant relevance for evaluating current accuracy. ...
This study examines Islamabad's landscape changes over four decades, attributing land degradation to shifts in land use and cover. Using Landsat imagery from 1980 to 2023, it analyzes urban growth in five categories. By employing the normalized difference vegetation index (NDVI) and normalized difference built-up index, it notes built-up areas expanding to 61% by 2023, agricultural land contraction, and fluctuating forest cover. Water bodies and bare land decrease significantly. With high accuracy values, NDVI fluctuates from +0.4523 in 1980 to +0.1596 in 2010, rebounding to +0.4422. Fluctuations in barren soil, vegetation, and built-up areas potentially contribute to temperature and rainfall changes. The study explores LULC and land surface temperature correlation. Surveyed respondents (755) express concerns about environmental changes, anticipating reduced rainfall and increased drought. Valuable for sustainable development goals, the study informs policy formulation for effective urban planning and land use control.
... • Accuracy assessment: Evaluation of precision accuracy is essential in evaluating various image-processing procedures in image classification (Ibrahim Mahmoud, Duker, Conrad, Thiel, & Shaba Ahmad, 2016;Lin, Wu, Tsogt, Ouyang, & Chang, 2015). The error matrix is the most general and mutually beneficial to current accuracy outcomes (Lu, Li, Moran, & Hetrick, 2013). ...
A GIS-based approach was used in this study to assess 10 years of land-use change in the lower Shivalik landscape of the Western Himalayas, India. The landscape encompasses two major protected areas which are home to a thriving population of large mammals. The main objective was to identify the changes in the land use pattern, specifically after forming a new tiger reserve in the landscape. Landsat 8 and 4 imagery were used for the time series analysis for the years 2018, 2013, and 2008, respectively. The change was calculated using nine land use classes, with mixed forest showing the highest change value, followed by agriculture, grassland, and scrub. The dense forest area increased immensely after the formation of the new tiger reserve. The results for dense and mixed forest classes also identified less fragmentation in the number of patches during the same time. Even though most of the landscape is within the boundaries of a protected area, the change in land use forms is noticeable. As development activities continue to expand, this region will face increased strain, which will impact the area’s natural biodiversity. To protect that, a long-term conservation management effort is required.
... It is possible to apply algorithms to correct the effects due to Earth's atmosphere [155], [157], [282], making some assumptions such as the horizontal homogeneity of the atmosphere, or the flatness of the ocean. However, these atmospheric corrections do not always result in a significant increase in the classification accuracy when using multispectral images [249], and they are not as frequent as water column corrections, which is why we consider them as optional. ...
... Nevertheless, when compared to other classification methods such as Support Vector Machine (SVM) or Neural Networks (NN), MLH classifiers appear to be less efficient, be it for land classification [3], [219], [220], [249], [411] or for coastline extraction [181], [279]. A comparison of some algorithms applied to crop classification also confirms that SVM and NN perform better, with an accuracy of more than 92% [229]. ...
The ongoing crisis of climate change necessitates the development of effective methods for monitoring and mapping environmental features and species to ensure their preservation. This thesis explores the application of machine learning algorithms to efficiently map coral reefs using multispectral satellite images. The Maupiti lagoon in French Polynesia serves as a case study. The research led to the production of an automated tool capable of generating coral reef maps from satellite images. Moreover, the tool can be adapted to map other ecosystems, such as forests or ice sheets, provided that the model is retrained with relevant data.
To begin, a comprehensive literature review investigates current methods and trends in utilizing machine learning algorithms for coral reef mapping. Then, the attempts to develop the tool led us to face the special case of compositional data, which are data carrying relative information and lying in a mathematical space known as simplex. Adaptations of conventional methods are required to address the specific characteristics of this space.
First, in response to data imbalance, an oversampling technique is developed specifically for compositional data. Additionally, a spatial autoregressive model based on the Dirichlet distribution is formulated to account for spatial effects that may arise in the mapping process.
Finally, we present the implementation of our final mapping tool. To achieve the desired objective, a two-staged classification process is implemented, combining pixel-based and object-based approaches. This technique enables the tool to achieve an accuracy exceeding 85% with 15 classes.
The research contributes novel solutions for handling compositional data and delivers a high-performing mapping tool for coral reef ecosystems, aiding in environmental management and conservation efforts.
... Typically, the alteration of land use modifies the purpose of land to be most suitable for human activity [1,3,4]. Typical factors that alter land use are socioeconomic activities and population growth [5,6], natural resources [7][8][9], and the effects of structures [3,5,6,10,11], land policy [12,13], and modernization [14,15]. Land use changes in functions, structures, and environmental conditions by modernization become increasingly extensive to adapt to population growth [16][17][18][19][20]. ...
Under the effects of saltwater intrusion from rising sea water levels, climate change, and socioeconomic issues, the Nga Nam district in Vietnam has suffered damage to its agriculture and changes in agricultural land use. This study aimed to investigate the factors that influenced land use changes and to propose approaches to limit the changes in agricultural land use. The damage caused by saltwater intrusion on agricultural production was evaluated via the use of secondary data collected from the Department of Infrastructure Economics of the Nga Nam district in the period of 2010–2021. The results show that during the 2010–2015 period, agricultural production areas were affected in 2010, 2012, and 2015. In the period of 2015–2021, the trend of saltwater intrusion along the damaged area remarkably decreased due to the work of saltwater-preventing structures. In this period, the area of annual plants increased, while that of perennial trees decreased. In the area comprising annual plants, the area using the triple rice land use type converted into an area using the double rice and double rice–fish ones. Lands for perennial trees transitioned from mixed farming to specialized farming to raise the economic efficiency for farmers. These changes were affected by four main factors: the physical factor, the economy, society, and the environment. The environmental and economic factors were seen to play the most important role as drivers of changes in land use. The factors of saltwater intrusion and acid-sulfate-contaminated soil, consumer markets, floods, drought, profit, and investments were noted to be significant drivers in agricultural land use change. Thus, both structural and non-structural approaches are suggested to inhibit the safeguard changes in the future.
... Furthermore, this study utilized the component substitution-based panchromatic sharpening (pansharpening) algorithm to ensure that all spectral bands had the exact same spatial resolution. Despite its ability to increase spatial resolution, pansharpened images have been reported to improve the accuracy of classification results (Lin et al., 2015;Phiri et al., 2018). Because Sentinel-2 already has 10 m bands, other bands' resolutions can be improved to match it (Wang et al., 2016). ...
Satellite data are essential during wildfires for understanding its adverse effects and improving the effectiveness of rapid disaster management. However, existing techniques used for damage assessments are inaccurate and lack automation. In this study, we propose an integrated machine learning approach with auto-generated training samples for a rapid wildfire disaster response framework using Sentinel-2 imagery at 10 m resolution from Google Earth Engine (GEE). First, training samples of burned areas were obtained by utilizing textural data based on features that had changed because of the wildfire, and samples of unburned areas were obtained using the normalized difference vegetation index (NDVI). The images were categorized as burned and unburned images using the object-based image analysis (OBIA) classification method. Finally, using the classified maps, burn severity maps and estimated pixel counts for each severity class were generated and compared. The proposed method was implemented to put out a wildfire that broke out in Uljin, Gyeongsangbuk-do, South Korea in March 2022 and the transferability of the model was evaluated in Gangneung, Gangwon-do, South Korea. The study findings indicate that the random forest (RF) classifier acquired the greatest overall accuracy (OA) of 97.6 % in Uljin; additionally, the model transferability performed well in Gangneung with an OA of 93.8 %. The RF also generated the fewest pixels of the unchanged class when the burn severity map was evaluated. Overall, our study proposes a quick and automated approach for estimating wildfire damage that could be used for immediate mitigation actions.
... Accuracy evaluation processes decide the reliability of the spatial information generated from remote sensing images for accurate image classification [77,78]. Remotely sensed spatial information is both reliable and accurate when used in integration with ground control points that serve as a reference [79]. ...
Understanding the change dynamics of land use and land cover (LULC) is critical for efficient ecological management modification and sustainable land-use planning. This work aimed to identify, simulate, and predict historical and future LULC changes in the Sohag Governorate, Egypt, as an arid region. In the present study, the detection of historical LULC change dynamics for time series 1984–2002, 2002–2013, and 2013–2022 was performed, as well as CA-Markov hybrid model was employed to project the future LULC trends for 2030, 2040, and 2050. Four Landsat images acquired by different sensors were used as spatial–temporal data sources for the study region, including TM for 1984, ETM+ for 2002, and OLI for 2013 and 2022. Furthermore, a supervised classification technique was implemented in the image classification process. All remote sensing data was processed and modeled using IDRISI 7.02 software. Four main LULC categories were recognized in the study region: urban areas, cultivated lands, desert lands, and water bodies. The precision of LULC categorization analysis was high, with Kappa coefficients above 0.7 and overall accuracy above 87.5% for all classifications. The results obtained from estimating LULC change in the period from 1984 to 2022 indicated that built-up areas expanded to cover 12.5% of the study area in 2022 instead of 5.5% in 1984. This urban sprawl occurred at the cost of reducing old farmlands in old towns and villages and building new settlements on bare lands. Furthermore, cultivated lands increased from 45.5% of the total area in 1984 to 60.7% in 2022 due to ongoing soil reclamation projects in desert areas outside the Nile Valley. Moreover, between 1984 and 2022, desert lands lost around half of their area, while water bodies gained a very slight increase. According to the simulation and projection of the future LULC trends for 2030, 2040, and 2050, similar trends to historical LULC changes were detected. These trends are represented by decreasing desert lands and increasing urban and cultivated newly reclaimed areas. Concerning CA-Markov model validation, Kappa indices ranged across actual and simulated maps from 0.84 to 0.93, suggesting that this model was reasonably excellent at projecting future LULC trends. Therefore, using the CA-Markov hybrid model as a prediction and modeling approach for future LULC trends provides a good vision for monitoring and reducing the negative impacts of LULC changes, supporting land use policy-makers, and developing land management.
... Effective management of land use and land cover is crucial in mitigating land degradation, climate change, and extreme rainfall events [4] [5]. Changes in land cover impact the atmosphere, climate, and biology of the Earth, affecting flooding, sedimentation, and stream habitats [6] [7] [8]. Conversion of forests, wetlands, and agricultural land into impervious urban surfaces yields economic benefits but poses environmental costs, increasing runoff and nonpoint source pollution [9] [10]. ...
The Agusan River basin is a lifeline for residents in Agusan del Norte, Agusan del Sur, and Davao del Norte. However, human activities have caused water contamination and siltation, leading to significant structural and physical changes in the river. This study utilized two machine learning classifiers, Support Vector Machine (SVM) and Random Forest (RF), within the Google Earth Engine (GEE) platform to assess the land use and land cover (LULC) changes from 2000 to 2020. The results unequivocally favored SVM, with higher accuracies of 95.53%, 95.61%, and 92.21% in 2000, 2010, and 2020, respectively. Notably, the study unveiled the substantial impact of LULC changes on critical water quality parameters, including turbidity, total suspended solids, and pH. These findings bear profound implications for the conservation and management of the Agusan River Basin, providing policymakers with invaluable insights for crafting interventions to preserve this invaluable natural resource.
... The satellite data were delivered at the product level of L2A, meaning that the values are presented as radiometrically corrected image pixels [39]. As the acquired images of the mariculture area exhibited excellent conditions without the presence of clouds, it was not necessary to perform atmospheric correction [40]. To process the acquired multi-spectral and panchromatic bands, we employed a three-step approach. ...
... In the following parts of this section, we will present the three major parts: (1) encoder based on CNN; (2) hierarchical lightweight Transformer; (3) detailed structure refinement. area exhibited excellent conditions without the presence of clouds, it was not necessary to perform atmospheric correction [40]. To process the acquired multi-spectral and panchromatic bands, we employed a three-step approach. ...
Precise delineation of marine aquaculture areas is vital for the monitoring and protection of marine resources. However, due to the coexistence of diverse marine aquaculture areas and complex marine environments, it is still difficult to accurately delineate mariculture areas from very high spatial resolution (VHSR) images. To solve such a problem, we built a novel Transformer–CNN hybrid Network, named TCNet, which combined the advantages of CNN for modeling local features and Transformer for capturing long-range dependencies. Specifically, the proposed TCNet first employed a CNN-based encoder to extract high-dimensional feature maps from input images. Then, a hierarchical lightweight Transformer module was proposed to extract the global semantic information. Finally, it employed a coarser-to-finer strategy to progressively recover and refine the classification results. The results demonstrate the effectiveness of TCNet in accurately delineating different types of mariculture areas, with an IoU value of 90.9%. Compared with other state-of-the-art CNN or Transformer-based methods, TCNet showed significant improvement both visually and quantitatively. Our methods make a significant contribution to the development of precision agricultural in coastal regions.
... A total of 1,200 samples were collected in six classes (water, asphalt/concrete/rock, buildings, low vegetation, forest, and soil). The segmented WV-2 image was then classified using the Support Vector Machine (SVM) algorithm (Aguilar et al., 2014;Lin et al., 2015;Wu et, al, 2017;Mugiraneza et al., 2019). The created DSM was used as an additional parameter. ...
Accurate monitoring and extraction of impervious surfaces are essential for urban planning and sustainable environmental management. Increasing urbanization has led to a significant increase in the extent of impervious surfaces, which, along with climate change, are the leading cause of increasingly frequent flooding in urban areas. To prevent flooding disasters in urban areas, flood hazard and risk analyses must be carried out. An imperviousness density model is one of the most important criteria in such analyses. In this study, an imperviousness density model of the city of Zadar was created using GIS-MCDA and four criteria (LULC, NDVI, slope and TWI). The criteria were extracted from WorldView-2 (WV-2) imagery and linearly standardized using the Fuzzy logic approach. The Analytic Hierarchy Process (AHP) was used to determine the final model for imperviousness density. The model with a spatial resolution of 0.5 m, based on the WV-2 imagery turned out to be much more detailed than existing publicly available models, such as the Copernicus imperviousness density model, which is based on Sentinel-2 imagery with a spatial resolution of 10 m.
... In some remote sensing applications, atmospheric correction is not essential. For instance, it has been argued that atmospheric correction does not improve land cover classification accuracy [53]. In multi-temporal change detection, atmospheric correction is typically unnecessary. ...
Multispectral sensors are important instruments for Earth observation. In remote sensing applications, the near-infrared (NIR) band, together with the visible spectrum (RGB), provide abundant information about ground objects. However, the NIR band is typically not available on low-cost camera systems, which presents challenges for the vegetation extraction. To this end, this paper presents a conditional generative adversarial network (cGAN) method to simulate the NIR band from RGB bands of Sentinel-2 multispectral data. We adapt a robust loss function and a structural similarity index loss (SSIM) in addition to the GAN loss to improve the model performance. With 45,529 multi-seasonal test images across the globe, the simulated NIR band had a mean absolute error of 0.02378 and an SSIM of 89.98%. A rule-based landcover classification using the simulated normalized difference vegetation index (NDVI) achieved a Jaccard score of 89.50%. The evaluation metrics demonstrated the versatility of the learning-based paradigm in remote sensing applications. Our simulation approach is flexible and can be easily adapted to other spectral bands.
