Land Mapping Research Articles

Applying multispectral UAV imagery to delineate in and near stream cover along a small urban stream

AbstractTraditional remote sensing methods are rarely applied to headwater streams because of a mismatch in spatial scale. With improved technology, remote sensing using unoccupied aerial vehicles enables imagery to be collected at high spatial and temporal resolution. However, these innovations have been used less frequently to detect changes within the water column. In addition, it is unclear whether classification methods developed along a single reach can be transferred through space (to other reaches) and through time, or how much information is needed to perform such classifications. This study combines methods of remote sensing, image processing, and machine learning to classify land cover and submerged aquatic vegetation along four urban stream reaches (170–325 m). A linear discriminant analysis (LDA) model was developed to provide land and water cover classification maps using training data. This method proved to be robust when classifying land cover along a single reach with minimal training data required. Using 200 pixels per land cover class resulted in 100% classification confidence for more than 93% of the pixels; when reducing this to only 50 pixels per land cover class, LDA yielded 100% classification confidence for nearly 80% of the total pixels. Through attempts to transfer relationships across reaches and flight dates, we found a greater percentage of misclassified pixels (upwards of 45% misclassification for flights on one date) when classifying across reaches on a single date as opposed to classification along a single reach for multiple dates. Overall, we recommend passive optical approaches, like the one used here, consider lighting conditions, reach orientation, and shading in data acquisition planning to mitigate the uncertainty they may introduce in delineating water column quality and cover.

Interoperability and Integration: An Updated Approach to Linked Data Publication at the Dutch Land Registry

Kadaster, the Dutch National Land Registry and Mapping Agency, has been actively publishing their base registries as linked (open) spatial data for several years. To date, a number of these base registers as well as a number of external datasets have been successfully published as linked data and are publicly available. Increasing demand for linked data products and the availability of new linked data technologies have highlighted the need for a new, innovative approach to linked data publication within the organisation in the interest of reducing the time and costs associated with said publication. The new approach to linked data publication is novel in both its approach to dataset modelling, transformation, and publication architecture. In modelling whole datasets, a clear distinction is made between the Information Model and the Knowledge Model to capture both the organisation-specific requirements and to support external, community standards in the publication process. The publication architecture consists of several steps where instance data are loaded from their source as GML and transformed using an Enhancer and published in the triple store. Both the modelling and publication architecture form part of Kadaster’s larger vision for the development of the Kadaster Knowledge Graph through the integration of the various linked datasets.

Estimation of Groundwater Recharge in Kumamoto Area, Japan in 2016 by Mapping Land Cover Using GIS Data and SPOT 6/7 Satellite Images

Agricultural fields, grasslands, and forests are very important areas for groundwater recharge. However, these types of land cover in the Kumamoto area, Japan, were damaged by the Kumamoto earthquake and heavy rains in 2016. In this region, where groundwater provides almost 100% of the domestic water supply for a population of about 1 million, quantitative evaluation of changes in groundwater recharge due to land cover changes induced by natural disasters is important for the sustainable use of groundwater in the future. The objective of this study was to create a land cover map and estimate the groundwater recharge in 2016. Geographic information system (GIS) data and SPOT 6/7 satellite images were used to classify the Kumamoto area into nine categories. The maximum likelihood classifier of supervised classification was applied in ENVI 5.6. Eventually, the map was cleaned up with a 21 × 21 kernel filter, which is larger than the common size of 3 × 3. The created land cover map showed good performance of the larger filter size and sufficient validity, with overall accuracy of 91.7% and a kappa coefficient of 0.88. The estimated total groundwater recharge amount reached 757.56 million m3. However, if areas of paddy field, grassland, and forest had not been reduced due to the natural disasters, it is estimated that the total groundwater recharge amount would have been 759.86 million m3, meaning a decrease of 2.30 million m3 in total. The decrease of 2.13 million m3 in the paddy fields is temporary, because the paddy fields and irrigation channels have been improved and the recharge amount will recover. On the other hand, since the topsoil on the landslide scars will not recover easily in natural conditions, it is expected to take at least 100 years for the groundwater recharge to return to its original state. The recharge amount was estimated to decrease by 0.17 million m3 due to landslides. This amount is quite small compared to the total recharge amount. However, since the reduced recharge amount accounts for the annual water consumption for 1362 people, and 12.1% of the recharge decrease of 1.41 million m3 each year to fiscal year 2024 is expected by municipalities, we conclude that efforts should be made to compensate for the reduced amount due to the disasters.

‘Compiled from Official Records’: Mapping Kansas Territory before the Civil War

ABSTRACT Tension between pro- and anti-slavery factions during the delineation and mapping of Kansas Territory in the 1850s, as Euro-American settlement moved west of the Mississippi River, permeated local politics and commerce. Despite the standardized surveying system employed by the U. S. General Land Office, this tension was reflected in township or sectional state maps that were produced during this time period. Using government surveys and reports documenting the progress of township surveys, commercial map publishers and land agents produced maps with the purpose of promoting quick land sales and profits. Yet the profit motive is not the only one apparent in these maps, and the history of their production is rife with intriguing stories involving conflicts of interest for government employees and the pro- and anti-slavery politics that dominated this critical period in U. S. history.

Clima Urbano e Ilhas de Calor no Miolo Urbano na Cidade de Salvador (BA)

O objetivo desta pesquisa foi analisar as ilhas de calor na cidade de Salvador nos bairros do Cabula e Pernambués ambos localizados no miolo urbano da cidade. Foram discutidos a relevância dos fatores geográficos de localização, altitude, influência dos sistemas de brisas marítimas e continentais, assim como o efeito do aquecimento das superfícies devido ao uso do solo urbano. Foi utilizada a concepção teórico-metodológica do Sistema Clima Urbano. Neste contexto, foram gerados mapas de usos dos solos das localidades através do programa Arcview 9.1. Posteriormente, foram efetuadas tomadas das temperaturas de superfície através de termômetros sensores de infravermelho nos diversos tipos de coberturas do solo em visitas técnicas à diversas ruas e avenidas nos bairros. Tais informações subsidiaram a organização do relatório final da pesquisa que se utilizou do Índice de Desconforto Térmico (ID). A utilização do ID detém extrema relevância pois busca estabelecer correlações entre as ilhas de calor e o desconforto físico que detém impacto direto na saúde e qualidade de vida das pessoas. Nos bairros do Pernambués e do Cabula foram identificadas classes de zona de desconforto. Porém, cabe destacar a relevância do fragmento da Mata Ombrófila Densa como elemento fundamental no estabelecimento de ilha de frescor no bairro Cabula.Palavras-chave: ilhas de calor, sistema clima urbano, fatores geográficos, uso do solo, desconforto térmico. Urban Climate, Heat Islands and Thermal Comfort in the Neighborhoods of Cabula and Pernambués in the Urban Center of Salvador (BA) A B S T R A C TThe objective of this research was to analyze the heat islands in the city of Salvador in the neighborhoods of Cabula and Pernambués both located in the urban core area of the city. The relevance of geographic factors of location, altitude, influence of sea and continental breeze systems, as well as the effect of heating of surface areas to urban land use were addressed. The theoretical and methodological conception of the Urban Climate System. In this context, maps of land uses of localities were generated through the arcview 9.1 programa. Subsequently, surface temperatures were made through infrared sensor thermometers through the various types of ground cover through technical visits to several streets and avenues in the neighborhoods. This information supported the organization of the final report of the research that used the Thermal Discomfort Index (ID). The use of ID has extreme relevance because it seeks to establish correlations between heat islands and physical discomfort that has a direct impact on people's health and quality of life. In the neighborhoods of Pernambués and Cabula, discomfort zone classes were identified. However, it is worth highlighting the relevance of the fragment of the Dense Ombrófila Forest as a fundamental element in the establishment of a frescor island in the Cabula neighborhood.Keywords: heat islands, urban climate system, geographic factors, land use, thermal discomfort.

Land use/Land Cover Dynamics in Pioneer Fronts and Implications on Livelihoods: Insights from Nkuh and Nkuv on the Bui Plateau

Land use dynamics in pioneer fronts in Sub-Saharan Africa is recurrent; yet, stakeholder interests and the various changes in land-use practices are still to be fully mainstreamed in resource use practices. The implications for livelihood improvement are indicative of the attracting force of these areas to different stakeholders. This study sets out to: 1. Map land use and land cover change in Nkuh and Nkuv pioneer fronts in the Bui Plateau; 2. Identify stakeholders and interests in pioneer fronts; 3. Understand land use change practices and implications for livelihoods. The study used diachronic analysis accompanied by 7 focus group discussions, 9 key informant interviews across native authorities and some government delegations on thematic analysis and narratives. The results revealed that small agroplantations are the major land-use changes from the existing rangelands and remnants of natural forests. Farmers from neighboring villages have migrated and settled in pioneer fronts, practicing agriculture through expansion, stabilization and consolidation. Diversification and adoption of new techniques like agro-forestry, agro-plantations (oil palms, fruit trees, cocoa) is growing amongst farmers, especially among return migrants, bureaucrats and land-use change/ land-use practices have important implication for livelihood improvement for the population implicated with an increase in output. Further studies can focus on how local endogenous processes and power asymmetries can improve resource use outcomes.

An Introduction to the Chinese High-Resolution Earth Observation System: Gaofen-1~7 Civilian Satellites

The Chinese High-resolution Earth Observation System (CHEOS) program has successfully launched 7 civilian satellites since 2010. These satellites are named by Gaofen (meaning high resolution in Chinese, hereafter noted as GF). To combine the advantages of high temporal and comparably high spatial resolution, diverse sensors are deployed to each satellite. GF-1 and GF-6 carry both high-resolution cameras (2 m resolution panchromatic and 8 m resolution multispectral camera), providing high spatial imaging for land use monitoring; GF-3 is equipped with a C-band multipolarization synthetic aperture radar with a spatial resolution of up to 1 meter, mostly monitoring marine targets; GF-5 carried 6 sensors including hyperspectral camera and directional polarization camera, dedicated to environmental remote sensing and climate research, such as aerosol, clouds, and greenhouse gas monitoring; and GF-7 laser altimeter system payload enables a three-dimensional surveying and mapping of natural resource and land surveying, facilitating the accumulation of basic geographic information. This study provides an overview of GF civilian series satellites, especially their missions, sensors, and applications.

Brigham Young and the Expansion of the Mormon Faith

Brigham Young and the Expansion of the Mormon Faith

КАРТОГРАФИРОВАНИЕ РАСТИТЕЛЬНОГО ПОКРОВА ПЕРМСКОГО КРАЯ ПО СПУТНИКОВЫМ СНИМКАМ LANDSAT

The paper deals with the methodology and results of Landsat-based vegetation cover mapping for the Perm region. Initial Landsat images were obtained in 2016–2020. The map building technique is based on the supervised classification of satellite images and subsequent post-processing. This technique involves the use of a number of additional sources, in particular, the results of global-Landsat-based mapping of forest disturbances, water surface, and arable lands, as well as reforestation areas on abandoned agricultural lands. As a result, a map with a spatial resolution of 30 m (which corresponds to a scale of 1:100,000) has been created. The map legend includes 19 thematic classes, 11 of them contain information on forest vegetation. The accuracy assessment of the obtained data was carried out with the use of a MODIS-based map of the vegetation cover of Russia and also forest inventory data on two forestries of the Perm region. The highest classification accuracy is typical for dark-coniferous and pine forests (it is about 70% according to the map of the vegetation cover of Russia, and up to 75% according to the forest inventory data). Deciduous forests are recognized with the lowest accuracy since, according to the classification results, they were partly categorized as mixed forests (with a predominance of deciduous species). The practical use of the created map of the vegetation cover may include estimation of long-term changes for individual vegetation classes (in particular, for intact forest landscapes), or various calculations based on the species composition and age structure of the forests. The compiled map of the vegetation cover of the Perm region is available at https://figshare.com/s/98d29e83d1f2039b2528.

Analysis of Surveying and Mapping Method of Landownership and Environmental Resources Confirmation Based on GPS Technology.

The establishment of the agricultural and forestry land management information system is predicated on the acquisition of spatial positioning data of agricultural and forestry land, i.e., the surveying and mapping of agricultural and forestry land. It also serves as the central component of the overall management information system. It is necessary to find solutions to the issues of large plot areas and far-reaching boundary lines in light of the current situation of land right confirmation. With its high efficiency, the use of GPS technology for land right confirmation can not only increase work productivity and speed up construction but also lower operating costs. The method of confirming landownership through surveying and mapping is studied in this paper using GPS technology. With respect to various land types, various classification methods have varying degrees of classification accuracy. This method is one of the three algorithms that classify green land, which includes grassland, cultivated land, and forest land; however, it does not clearly distinguish between forest land and grassland, with forest land having an average classification accuracy of 58.69 percent. The average accuracy of classifying forest land is 73.14 percent. The classification accuracy of forest land using this method is 88.45 percent, which is a relatively high percentage. It can be seen that this method is more accurate in identifying minute differences between ground objects. This is demonstrated by comparing the accuracy of forest land classification with that of other methods. A lot of surveying and mapping work has been done on the assumption that urban control networks have been established in many cities. The most ideal option is to combine GPS technology with high-precision photogrammetry.

Identification, Characterization and Mapping of Potential Irrigable Areas in Ziway Micro Watershed

Irrigation land suitability assessment and mapping for irrigation purpose is important to utilize the land resources efficiently. This study was initiated to assess, evaluate and develop map of the land resources which is potentially suitable for surface irrigation in ziway micro watershed by using Geographic Information System (GIS). The evaluation of land in terms of the suitability classes was based FAO guideline for land evaluation. Multi-criteria decision evaluation method and suitability factors were used such as, soil data, slope, land use/cover for evaluate the physical land characteristics of the study area of surface irrigation and suitability map was developed. After evaluating the physical land capability for surface irrigation, irrigation suitability map was developed. The weighted overlay analysis gave 70.1 and 13.3% of the study area is lies in the range of very high suitable to marginally suitable for irrigation. Thus, the overall suitability shows that potentially irrigable land suitable for surface irrigation is about 83.4% of the area. Therefore, based on results, farmers, decision makers, investors, planners and policymakers at the local, regional and national levels and the government should invest in those suitable areas for irrigation.

Mapping urban form and land use with deep learning techniques: a case study of Dongguan City, China

Precise urban form and land use data are crucial for various modelling simulations. Approaches using spectral features of remote sensing (RS) images have been widely adopted to capture land surface patterns. However, challenges arise concerning the accurate classification of built areas due to high levels of heterogeneity. An effective way to address this issue is to incorporate spatial contextual information. Deep learning techniques have recently been applied to RS image classification, and impressive results have been reported. This research undertook a case study of Dongguan City, which is a core Chinese city characterised by high density and heterogeneity. A culturally neutral classification scheme called local climate zone was adopted for land surface classification. The default random forest classification was used as a benchmark, and the moving window approach and several pretrained convolutional neural network (CNN) models were also applied for comparison. The moving window approach achieved the highest mapping accuracy with a window size of 5 × 5. Although the CNN models failed to achieve state-of-the-art results, they still exhibited an excellent performance considering the small number of input features and small input patch size. They can also reduce the salt-and-pepper phenomenon effectively. [Received: October 23, 2020; Accepted: January 24, 2021]

Implementation of Land Value Zone Regulation by the Land Office inthe Ex-Besuki Residence

Soil is part of the earth’s surface that plays an important role in the life of living things. Humans use land to carry out all life activities. Ministry of Agrarian and Spatial Planning/National Land Agency, where the agrarian and spatial planning sector is managed by the Ministry of Agrarian and Spatial Planning (ATR), while the land sector is managed by BPN. As a result, there is a large difference between the asking prices. Symptoms of rising land prices without going through a fair market mechanism generally follow the pattern of land use. Article 16 Paragraph (1) Government Regulation of the Republic of Indonesia Number 128 of 2015 states that the Land Value Zone is the market value determined by the Land Office of Jember Regency and Bondowoso Regency. Jember Regency and Bondowoso Regency as government representatives continue to improve land mapping methods and present information on Land Value Zone maps. These problems are: 1). What is the method used by the Land Office in the former Besuki Residency in determining accurate land value zoning?, 2). What is the relationship between Spatial Planning as one of the determinants of Land Value Zones?, 3). The former Besuki Residency Land Office in controlling land prices using the Land Value Zoning method? The method of analysis was carried out to determine the value of the soil in each zone and to find out the average indication value as the value of the soil indication used as the value of the land in each zone of land value (ZNT). The modeling results become a formulation for estimating the value of land in the future period. Thematic maps of Land Value Zones are represented by administrative areas. The estimation model of land value perception is a formulation model of land value perception which is the result of the model from year to year which has been updated and tested for reliability. So it can be concluded that the model results are close to the actual land value perception pattern that occurs in the field. The results of this modeling can be used as a formulation for updating land market value data at the Land Offices of Jember Regency and Bondowoso Regency, so that it can be a method for optimizing regional income through land tax revenues which will be managed by Jember Regency and Bondowoso Regency.

Integrated Analytical Hierarchical Process and Geographical Information System for Allocation of Compatible Land Uses along Uluguru Mountain Slopes

The northern slope of the Uluguru mountain, that falls under the sovereignty of Morogoro’s urban area, has steadily become populated and connected with uncontrolled human activity, which has had a harmful effect on the ecosystem. The rapid conversion of natural forests to farms and settlements has a severe effect on biodiversity and the land’s productive capacity. In order to assist the identification of compatible land uses for managing degradation and restoration of degraded land, as well as ensuring the long-term use of natural resources, this study applied the integration of Geographical Information System and Analytical Hierarchical Process. The land resources of the research area were identified using a Geographical Information System to guide in the evaluation of various land uses’ suitability. Land resource values were generated from different sources of data whereby elevation, slope, temperature, rainfall, soil properties, soil moisture index, and land surface temperature classifications were obtained. The land resource classification values throughout the study area were used to create land mapping units. The results of the criteria classification were integrated into questionnaires together with proposed compatible land uses obtained from the literature review. These well-structured questionnaires were used to retrieve expert opinions on land use allocation from environmental beneficiary institutions in the area. The influence of criteria on each suggested land use was assessed accordingly based on the score provided by Saaty’s scale. The weight of each criterion at each land mapping unit toward proposed compatible land uses for mapping purposes was calculated using the Analytical Hierarchical Process (AHP) technique. The weighted criteria produced by the AHP technique were integrated into GIS using the weighted overlay method to produce a map that reflects expert judgments on mountain slope planning for long-term natural resource management. A literature review reveals that conservation agriculture, agroforestry, and forest land use types are compatible in the management of natural resources in the area, while settlements have to be integrated to accommodate the existing situation. The integration of GIS and AHP produced a plan that consists of conservation agriculture that covers the majority of the study area (50%) and is generally found in the foothills of the mountains up to land mapping unit 3. Agroforestry is the second-largest land use, accounting for 19% of the study area and being concentrated in the second and third land mapping units. Settlements, which occupy 17% of the study area and are mostly located at the foothills of the mountain, are the third most covered land use. Finally, forest land use is distributed at the top of the research area, inside land mapping units 4 and 5, and accounts for 13% of the total study area. According on the findings of this study, a sustainable land use plan is recommended. Economic activity that could assist in the management of natural resources would be advantageous to both parties. Planning of the mountainous slopes within urban areas that are not designated as conservation zones should be done with great care, and only economic activities that assist management of natural resources should be permitted.

3-D Bi-directional LSTM for Satellite Soil Moisture Downscaling

Soil moisture is a crucial parameter of hydrological processes as it affects the exchange of water and heat at the land/atmosphere interface. Regional hydrological applications (floods and modeling of small basins) and agricultural applications (irrigation and agricultural land mapping) require daily soil moisture (SM) values having a spatial resolution of at least 1-km. This requirement is currently unmet by existing satellite missions. Notably, SM has variability over three dimensions. As such, accurate prediction of satellite SM requires multiple bidirectional spectra-spatiotemporal analyses. However, current state-of-the-art SM downscaling models can not yet fulfill this requirement. This paper proposes a new bi-directional LSTM model dubbed the three-dimensional bi-directional LSTM (3D-Bi-LSTM), which downscales the Soil Moisture Active Passive (SMAP) global daily 9-km SM to daily 1-km SM. In the proposed downscaling model, the region-specific soil moisture indices (SMIs) are first extracted using a covariance-adaptive convolutional neural network (CNN) to support the extraction of important distinctive information from multispectral data. Next, the CNN output is provided to the 3D-Bi-LSTM to perform the bi-directional analysis of spatial correlation within a feature and spectral correlation between features over multiple time instants. Experimental results demonstrate the proposed model outperforms state-of-the-art networks. An ablation study, transferability assessment, and feature importance study further demonstrate the proposed 3D-Bi-LSTM’s efficiency.

The Role of Machine Learning in Remote Sensing for Agriculture Drought Monitoring: A Systematic Review

Agricultural drought is still difficult to anticipate even though there have been developments in remote sensing technology, especially satellite imagery that is useful for farmers in monitoring crop conditions. The availability of open and free satellite imagery still has a weakness, namely the level of resolution is low and coarse with atmospheric disturbances in the form of cloud cover, as well as the location and period for taking images that are different from the presence of weather stations on Earth. This problem is a challenge for researchers trying to monitoring agricultural drought conditions through satellite imagery. One approach that has recently used is high computational techniques through machine learning, which is able to predict satellite image data according to the conditions of mapping land types and plants in the field. Furthermore, using time series data from satellite imagery, a predictive model of crop cycles can be regarding future crop drought conditions. So, through this technology, we can encourage farmers to make decisions to anticipate the dangers of agricultural drought. Unfortunately, exploration of the use of machine learning for classification and prediction of agricultural drought conditions has not conducted, and the existing methods can still improve. This review aims to present a comprehensive overview of methods that used to monitor agricultural drought using remote sensing and machine learning, which are the subjects of future research.

Improvement of the efficiency of using agricultural land

The goal is to find ways to increase the efficiency of agricultural land turnover using GIS technologies. Methods – monographic, analytical, abstract logical, economic and statistical. Results - the presence of a significant potential of unused agricultural land, the need to develop a mechanism for transferring one type to another, drawing up a map of land resources that are not in operation, taking into account the quality condition depending on the bonitet scores based on the example of Akmola region are justified. It is shown that a number of changes have been made to the Rules of the rational use of agricultural land, in particular, it is necessary to fill out a web portal for their application (crop rotations, a field history book, etc.). It was revealed that in recent years, there has been a steady decrease in the State stock and the increase in the area of agricultural land. The authors state that today there are no standards regulating their transformation and the definition of the corresponding type. It is necessary to create a system for returning unused land plots to agricultural production based on geographic information systems. Space monitoring of land use was carried out, on the basis of which the maps of waste lands for 2021 and the distribution of bonitet points in Akmola region were compiled. Conclusions – at the legislative level, it is necessary to establish a legal regime regarding the land fund; when granting plots for land use, it is required to determine, first of all, the quality condition, belonging to a certain category of agricultural land and assignment to the category of targeted agricultural use. The lack of clear criteria for the suitability of this category for a specific use prevents the acceleration of the process of bringing unused arable land into use.

Mapping Land Use Land Cover Changes and Their Determinants in the Context of a Massive Free Labour Mobilisation Campaign: Evidence from South Wollo, Ethiopia

Northern Ethiopia is characterised by fragile mountain eco-systems that are highly susceptible to land degradation, impacting food security and livelihoods. This study appraises Land Use Land Cover Changes (LULCC) and their determinants from 2000 to 2020 in Dessie Zuria and Kutaber Woredas. It explores the LULCC and the key anthropogenic drivers of the change over the past 20 years through a mix of satellite imagery and a survey of local understandings. Six land use types (agriculture, forest, area closure, grazing, settlement and bare land) were mapped from satellite imagery that was acquired from Landsat 7 for the years 2000, 2005, and 2010, and Landsat 8 and OLI multispectral imageries for the years 2015 and 2020 with a spectral resolution of 30-m obtained from USGS. The results showed that agricultural land increased from 29.68% in 2000 to 35.77% in 2020.Furthermore, settlement and grazing lands enlarged from 5.95% and 6.04%, respectively, to 8.31% and 6.35% during the same period, while bare land increased from 9.89% to 10.92% in 2020. On the contrary, forest and area closure decreased from 18.45% and 29.99% to 17.8% and 17.38%, respectively. Meanwhile, population growth, unrestricted grazing, losing a sense of ownership of protected area closures and forests, lack of cooperation, using the free labour mobilisation schemes for government-induced agendas, weak enforcement of laws and bylaws, and engaging farmers for extended days on the campaign were prominent determinants of the changes. This research has implications for development actors across land management and food security towards implementing sustainable land management in the area and beyond.

Mapping Land Use and Land Cover in the Upper Ciliwung Watershed Using Landsat Tree Cover (TC) Data

<p class='IJASEITAbtract'>Land use and land cover (LULC) mapping using Landsat Tree Cover (TC) data that we employed was digital classification by converting Landsat TC raster data into Landsat TC vector data and determining LULC classes in the attribute table based on percent TC criteria (interval TC- min - TC-max). The classification was adapted from the LCCS classification and partially modified. Compared to conventional digital image classification (supervised and unsupervised classifications), our digital classification method is easier and faster because Landsat TC data does not require pre-processing and reclassification to improve classification accuracy. Landsat TC classification accuracy was assessed against the interpretation of a very high spatial resolution (VHSR) image available in Google Earth (GE). The purpose of the study was to determine the ability of Landsat TC data paired with percent TC criteria of LULC adapted from the LCCS classification and validated with VHSR in GE for mapping LULC in the tropics. This study was conducted in the Upper Ciliwung watershed, which is located in Bogor Regency, West Java Province, Indonesia. LULC mapping using Landsat TC data paired with percent TC criteria of LULC adapted from the LCCS classification and validated with VHSR in GE provided a useful tool for producing LULC map in the Upper Ciliwung watershed. This study classified LULC in the Upper Ciliwung watershed consisting of settlements, closed forests, medium forests, opened forests, mix gardens, tea plantations, shrub lands, grasslands, and rainfed croplands paddy fields, fish fonds, and bare lands with overall accuracy of 91%.

Mapping land cover using a developed U-Net model with weighted cross entropy

High-quality and high-productivity land cover data as a critical proxy are urgently needed for various communities. Although efforts in mapping projects had been made, various architectures to answer the challenges of Big Data of remote sensing are still needed. Therefore, this paper developed an improved U-Net model with weighted cross entropy (WCE) to map land covers. The accuracy was assessed by confusion matrix, and compared with the other two alternative cross-entropy loss functions. The comparisons highlighted an issue that unbalanced sample space of training dataset is a major cause of lower mapping accuracy. Also, the higher accuracy of U-Net with WCE implied its ability to handle the issue. This paper suggests an alternative solution for mapping land cover to address the challenges.