Land use and land cover (LULC) changes are recognized as one of the most significant driver of environmental changes, mainly due to rapid urbanization. In this paper, an attempt has been made to appraise the ability of multi-layer perceptron-Markov chain analysis (MLP-MCA) integrated method to monitor and predict the future LULC change scenarios in Patna district, Bihar using remote sensing images. A supervised maximum likelihood classification method was applied to derive LULC maps from 1988, 2001, and 2013 Landsat Thematic Mapper (TM)/Enhanced Thematic Mapper Plus (ETM+)/Operational Land Imager (OLI) images, respectively. The LULC maps of 1988 and 2001 were employed to predict the LULC scenario for 2013 using MLP-MCA method. The predicted result was compared with the observed LULC map of 2013 to validate the method using kappa index statistics. Finally, based on the results, the future LULC change prediction for 2038 and 2050 was performed. The outcomes of this study reveal the rapid growth in ​built up area results in continuous decrease in agricultural lands.

A remote sensing aided multi-layer perceptron-Markov chain analysis for land use and land cover change prediction in Patna district (Bihar), India

Aeolian desertification is one of the most serious environmental and socioeconomic problems in arid, semi-arid, and dry subhumid zones. Understanding desertification processes and causes is important to provide reasonable and effective control measures for preventing desertification. With satellite remote sensing images as data source to assess the temporal and spatial dynamics of desertification from 1975 to 2010 in the Horqin Sandy Land, dynamic changes of aeolian desertification were detected using the human–machine interactive interpretation method. The driving factors of local desertification were analyzed based on natural and socioeconomic data. The results show that aeolian desertified land in the study area covered 30,199 km2 in 2010, accounting for 24.1 % of the study area. The total area of aeolian desertified land obviously expanded from 30,884 km2 in 1975 to 32,071 km2 in 1990, and gradually decreased to 30,199 km2 in 2010; aeolian desertified land represented an increasing trend firstly and then decreased. During the past 35 years, the gravity centers of desertified lands that are classified as extremely severe and severe generally migrated to the northeast, whereas those that are moderate and slight migrated to the northwest. The migration distance of severely desertified land was the largest, which indicated the southern desertified lands were improved during the last few decades. In addition, the climatic variation in the past 35 years has been favorable to desertification in the Horqin Sandy Land. Aeolian desertified land rapidly expanded from 1975 to 1990 under the combined effects of climate changes and unreasonable human activities. After the 1990s, the main driving factors responsible for the decrease in desertification were positive human activities, such as the series of antidesertification and ecological restoration projects.

Dynamics of aeolian desertification and its driving forces in the Horqin Sandy Land, Northern China.

Indonesian food production depends highly on Java Island, which holds the most fertile soils in the country but had limited area. The objective of the research was to analyse the availability of suitable land for agriculture in Tuban Regency, an agricultural regency in Java Island. Land suitability was evaluated with spatial multicriteria analysis, integrating soil order, land capability, elevation, slope, slope direction, land use/land cover, accessibility, and climate. Land availability was analysed, integrating the forest area status designation and the spatial pattern of regional official land use plan. The results indicated that suitable land for agriculture corresponds to 91% of the total study area, confirming the high soil fertility. Analysis of land availability then indicated that 18% of the area was both suitable and available for agriculture. Considering the actual land utilization, the future development of agriculture in the region has less than 7% of the land area left for agricultural expansion. The overall results showed the importance of looking for land allocated for agriculture outside Java Island to anticipate the need for food of a country with a high population growth rate and also developing planning for food production.

/pdf/assessing-the-suitability-and-availability-of-land-for-1d6jq90225.pdf

Assessing the Suitability and Availability of Land for Agriculture in Tuban Regency, East Java, Indonesia

Mapping submerged corals in Fiji from remote sensing and in situ measurements: applications for integrated coastal management

Assessing the spatial land use and land cover (LULC) information is essential for decision making and management of landscapes. In fact, LULC information has been changed dramatically in fast-growing cities. This results in wrong land use problems due to unplanned and uncontrolled urbanization. The planning and evaluating of limited natural resources under the pressure of a growing population can be possible when a precise land use management plan is established. Therefore, it is imperative to monitor continuous LULC changes for future planning. Remote sensing (RS) technique is used for determining changes in LULC in urban areas. In this study, we have focused on Izmit, which is one of a growing number of metropolitan cities where the impact of the spatial growing period on LULC has been assessed over the past 30 years by using RS data. We have utilized the segmentation process and supervised classification of Landsat satellite images for four different dates (1985, 1995, 2005, and 2015). The outcome of this research can be summarized by significant changes in the shares of urban areas and farmland LULC classes. The overall observed increase in urban area class is up to 2177 ha between 1985 and 2015 period and this dramatic change has resulted in the decline of 1211 ha of farmland. Another conclusion is that the new residential areas have been created to the north, south and east of Izmit during this period.

Monitoring urban growth by using segmentation-classification of multispectral Landsat images in Izmit, Turkey

SPOT multispectral data were compared statistically with 10 meters mesh numerical land use data in the study area near Tokyo. The numerical land use data have 16 categories and were produced from color aerial photographs by Geographical Survey Institute of Japan. This statistical analysis shows poor possibility of ‘land use’ classification from SPOT data and suggest to establish ‘land cover’ categories. Six types of land cover categories were established based on the above statistical analysis and aerial photographs for ground truth and were defined mainly by dividing two dimensional SPOT feature space into regions. The study area is classified into these land cover categories by decision tree method and examined with numerical land use data. The conclusions of this study are (1) Numerical geographical information is highly useful for analysis of remotely sensed data. (2) New method of defining land cover categories were proposed. (3) Six types of land cover classes cart be extracted from SPOT da...

Youji Mukouyama

Papers

Land cover classification using SPOT data