Development of Land-Use/Land-Cover Maps Using Landsat-8 and MODIS Data, and Their Integration for Hydro-Ecological Applications

Afrin, Sadia; Gupta, Anil; Farjad, Babak; Ahmed, M. Razu; Achari, Gopal; Hassan, Quazi K.

doi:10.3390/s19224891

Cited by 32 publications

(19 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An unsupervised classification scheme using the Iterative Self-Organizing Data Analysis Technique (ISODATA) was used to determine the threshold (cut-off) values needed to classify the NDVI images into vegetated and non-vegetated areas. ISODATA [28,30,31] is an iterative unsupervised classification algorithm, which minimizes the within cluster variability and categorizes the pixels into different number of classes based on statistics. The classification of the NDVI images was finally done for each year using the density slicing technique.…”

Section: Analysis Of Vegetationmentioning

confidence: 99%

Mapping the Recovery Process of Vegetation Growth in the Copper Basin, Tennessee Using Remote Sensing Technology

Blanton

Hossain

2020

GeoHazards

View full text Add to dashboard Cite

The Copper Basin (CB) of southeastern Tennessee, known as the Ducktown Mining District, is a classic example of forest and soil destruction due to extensive mining and smelting operations from the mid-1800s until 1987. The smelting operation released a sulfur dioxide by-product that formed sulfuric acid precipitation which, in combination with heavy logging, led to the complete denudation of all vegetation covering 130 km2 in CB. The area has since been successfully revegetated. This study used remote sensing technology to map the different episodes of this vegetation recovery process. A time series of Landsat imagery acquired from 1977 through 2017 at 10-year intervals was used to map and analyze the changes in vegetation cover in CB. These maps were used to generate a single thematic map indicating in which 10-year period each parcel of land was revegetated. Analysis shows that the extent of non-vegetated areas continuously decreased from about 38.5 to 2.5 km2 between 1977 and 2017. The greatest increase in vegetation regrowth occurred between 1987 and 1997, which was the period when all mining and smelting activities ceased. This research could be very useful to better understand the recovery process of areas affected by mining and smelting processes.

show abstract

Section: Analysis Of Vegetationmentioning

confidence: 99%

Mapping the Recovery Process of Vegetation Growth in the Copper Basin, Tennessee Using Remote Sensing Technology

Blanton

Hossain

2020

GeoHazards

View full text Add to dashboard Cite

show abstract

“…Recent years have witnessed great advances in LULC classification in tasks such as denoising, cloud shadow masking, segmentation, and classification [6][7][8][9]. Extensive algorithms have been devised with concrete theoretical bases, exploiting the spectral and spatial properties of pixels.…”

Section: Introductionmentioning

confidence: 99%

Deep Transfer Learning for Land Use and Land Cover Classification: A Comparative Study

Naushad¹,

Kaur

Ghaderpour

2021

Sensors

View full text Add to dashboard Cite

Efficiently implementing remote sensing image classification with high spatial resolution imagery can provide significant value in land use and land cover (LULC) classification. The new advances in remote sensing and deep learning technologies have facilitated the extraction of spatiotemporal information for LULC classification. Moreover, diverse disciplines of science, including remote sensing, have utilised tremendous improvements in image classification involving convolutional neural networks (CNNs) with transfer learning. In this study, instead of training CNNs from scratch, the transfer learning was applied to fine-tune pre-trained networks Visual Geometry Group (VGG16) and Wide Residual Networks (WRNs), by replacing the final layers with additional layers, for LULC classification using the red–green–blue version of the EuroSAT dataset. Moreover, the performance and computational time are compared and optimised with techniques such as early stopping, gradient clipping, adaptive learning rates, and data augmentation. The proposed approaches have addressed the limited-data problem, and very good accuracies were achieved. The results show that the proposed method based on WRNs outperformed the previous best results in terms of computational efficiency and accuracy, by achieving 99.17%.

show abstract

“…Several previous studies have extensively used Google Earth Pro for investigating and analyzing natural resources, hydrological balance, ecological stability, LULC changes, navigation, agricultural watersheds, geosciences, and archeological findings from across the globe [11,13,34,37,68,71]. Afrin et al [1] developed LULC maps for the year 2016 using Landsat-8 and MODIS data for hydroecological applications on the Athabasca river watershed. Their results served as important decision support tools for policy-makers and local regulatory authorities of the Athabasca river.…”

Section: Introductionmentioning

confidence: 99%

Investigating impact of land-use and land cover changes on hydro-ecological balance using GIS: insights from IIT Bombay, India

Srivastava

Chinnasamy

2021

SN Appl. Sci.

View full text Add to dashboard Cite

The present study, for the first time, examined land-use land cover (LULC), changes using GIS, between 2000 and 2018 for the IIT Bombay campus, India. Objective was to evaluate hydro-ecological balance inside campus by determining spatio-temporal disparity between hydrological parameters (rainfall-runoff processes), ecological components (forest, vegetation, lake, barren land), and anthropogenic stressors (urbanization and encroachments). High-resolution satellite imageries were generated for the campus using Google Earth Pro, by manual supervised classification method. Rainfall patterns were studied using secondary data sources, and surface runoff was estimated using SCS-CN method. Additionally, reconnaissance surveys, ground-truthing, and qualitative investigations were conducted to validate LULC changes and hydro-ecological stability. LULC of 2018 showed forest, having an area cover of 52%, as the most dominating land use followed by built-up (43%). Results indicated that the area under built-up increased by 40% and playground by 7%. Despite rapid construction activities, forest cover and Powai lake remained unaffected. This anomaly was attributed to the drastically declining barren land area (up to ~ 98%) encompassing additional construction activities. Sustainability of the campus was demonstrated with appropriate measures undertaken to mitigate negative consequences of unwarranted floods owing to the rise of 6% in the forest cover and a decline of 21% in water hyacinth cover over Powai lake. Due to this, surface runoff (~ 61% of the rainfall) was observed approximately consistent and being managed appropriately despite major alterations in the LULC. Study concluded that systematic campus design with effective implementation of green initiatives can maintain a hydro-ecological balance without distressing the environmental services.

show abstract

Development of Land-Use/Land-Cover Maps Using Landsat-8 and MODIS Data, and Their Integration for Hydro-Ecological Applications

Cited by 32 publications

References 41 publications

Mapping the Recovery Process of Vegetation Growth in the Copper Basin, Tennessee Using Remote Sensing Technology

Mapping the Recovery Process of Vegetation Growth in the Copper Basin, Tennessee Using Remote Sensing Technology

Deep Transfer Learning for Land Use and Land Cover Classification: A Comparative Study

Investigating impact of land-use and land cover changes on hydro-ecological balance using GIS: insights from IIT Bombay, India

Contact Info

Product

Resources

About