Artificial neural networks paddy-field classifier using spatiotemporal remote sensing data

Yamaguchi, Takashi; Kishida, Kazuya; Nunohiro, Eiji; Park, Jong Geol; Mackin, Kenneth J.; Hara, Keitaro; Matsushita, Kotaro; Harada, Ippei

doi:10.1007/s10015-010-0797-4

Cited by 9 publications

(6 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In India, around 75% of the total rainfall is concentrated over 4 months of monsoon (June-September) and, as a result, almost all the rivers carry heavy discharge during these four months. Around 12% of the national land area is prone to floods which means around 40 million hectares are prone to flood and annually on an average 8 million is affected by floods (Bechtel et al 2014;Yamaguchi et al 2010).…”

Section: Introductionmentioning

confidence: 99%

RETRACTED ARTICLE: Spatial and temporal analysis of flood hazard assessment of Cuddalore District, Tamil Nadu, India. Using geospatial techniques

Felix

Sasipraba

2020

J Ambient Intell Human Comput

View full text Add to dashboard Cite

Flood is a natural calamity and causes damage of life and property devastation. The main objective of this study was to analyse flood hazard and inundation area mapping of Paravanar sub-Basin. Flood generating factors, like elevation, slope, drainage density, rainfall, soil type and land use were analyzed and delineated flood zones using Geospatial techniques and multi criteria evaluation. The flood generating factor was computed by data integration, floodplain depiction, mapping, and evaluation. Various parameters such as Normalized difference vegetation index (NDVI), Normalized difference build-up index (NDBI), Normalized difference water index (NDWI) were acquired for performing Regression Analysis. This information can be further utilized for hydro-meteorological figures and Surge forecast. These data can be used in building hazard and risk maps for pre-flood prediction. The flood hazard threats in the southeast and in between southeast and west part of the Paravanar River basin are high flood hazard threat zone.

show abstract

Section: Introductionmentioning

confidence: 99%

RETRACTED ARTICLE: Spatial and temporal analysis of flood hazard assessment of Cuddalore District, Tamil Nadu, India. Using geospatial techniques

Felix

Sasipraba

2020

J Ambient Intell Human Comput

View full text Add to dashboard Cite

show abstract

“…Due to the development of satellite base remote sensing technologies with great precision for earth observation, the NDVI could be a powerful tool for long-term monitoring of dynamic vegetation cover for larger areas (Leroux et al, 2017;Piao et al, 2011;Zhou et al, 2020). NDVI has been used by several researchers for vegetation monitoring (Yang et al, 2011, Lan et al, 2009, crop cover assessment (El-Shikha, 2007), drought monitoring (Kim et al, 2008;Yamaguchi, 2010), and for agricultural drought evaluation at the national and global levels (Demirel et al, 2009;Zhang et al, 2009).…”

Section: O N L I N E C O P Ymentioning

confidence: 99%

A multiscale analysis and classification of normalized difference vegetation index value method in Kannad Taluka, Aurangabad District, using remote sensing and GIS

Garoon,

Mule

2023

JEB

View full text Add to dashboard Cite

Aim: The main objective of the present study is to quantify and assess the changes in vegetation cover by using NDVI values from the Kannad Taluka of Aurangabad district, Maharashtra, India. The changes were studied during the period 2013 to 2020 to identify the probable causes of change in NDVI. Methodology: The present study utilized Landsat images to evaluate and track the changes in vegetation cover by using the NDVI index values and classified in eight classes during seven years period. Results: Two of the major NDVI classifications of this area were agriculture and urban area which showed a significant decrease in the year 2020 while in the water bodies, dense forest, sparse forest, grass land mixed with shrubs, grass land and barren land were increased. Area covered by agriculture and urban area was found 36.40% and 4.47 % in 2013 and which was noted to reduce by 21.64% and 2.53 % in 2020. The water bodies, dense forest, sparse forest, grass land and shrubs, grass land and barren land were found to be 1.79%, 6.18%, 9.71%, 12.71%, 12.92%, and 15.82 % in the year 2013 and were increased up to 2.17%, 14.28%, 13.52%, 13.49%, 14.54% and 17.83 % in 2020, respectively. Interpretation: Area covered by agriculture has decreased by 14.76% in seven year period while the barren land increased by 2.01% in seven year period in Kannad Taluka. The loss of forest cover might be due to increased human population in the study area. Key words: Agricultural land, GIS, Kannad Taluka, Remote Sensing, Vegetation cover

show abstract

“…Various techniques and tools described in literature are about change detection in vegetation, and other attributes to analyse the satellite imageries like NDVI , ANN (Artificial Neural Net-work), and satellite image contrast enhancement (Table 2). They use discrete wavelet trans-form (DWT), and singular value decomposition (SVD), for increased spatial, accurate, and temporal coverages, [29][30][31][32][33][34]. The way of taking/receiving satellite imageries and big data done by innovative methodologies by using LIDAR, GNSS, unmanned aerial vehicles, drones etc [34][35][36].…”

Section: Literature Reviewmentioning

confidence: 99%

Geomorphologic Change in Nagavali River Basin: Geospatial Approach

Mishra

Patel

Mishra

et al. 2021

IJECC

View full text Add to dashboard Cite

The Nagavali river basin (NRB), along east coast of India investigated for its land use and land cover changes (LULCC) in the golden spike period of Anthropocene Epoch. Attempts made to assess the vicissitudes, causes, and consequences of natural resources, and soil/water resources of the NRB in last three decades as significant changes in hydro-climatic variables occurred. The interstate basin is well developed in lower reaches (north Andhra Pradesh) whereas upper stretches, South Odisha is less organized. GIS and remote sensing are efficient tools for an ideal study of LULCC of the area. Present work evaluates the dynamics of LULCC of NRB. LANDSAT-5, LANDSAT-8, of 1990, 2000, 2010 and 2020, respectively, were digitally classified for land use land cover mapping. The changing aspects of LULCC critically analyzed for three span, 1990–2000, 2000–2010 and 2010–2020. Through Normalized Difference Vegetation Index (NDVI) of the NRB examined carefully to assess the recent LULCC pattern. Major changes are sue to exchanges of areas are in between forest and built-up land followed by water body. The transformations are from forest to human habitation; especially built-up area that constitutes major percentage of the total landscape. The study shows that emphasis is necessary on more water consolidation projects in the upper Nagavali Basin considering the long-term LULC trend analysis.

show abstract

Artificial neural networks paddy-field classifier using spatiotemporal remote sensing data

Cited by 9 publications

References 5 publications

RETRACTED ARTICLE: Spatial and temporal analysis of flood hazard assessment of Cuddalore District, Tamil Nadu, India. Using geospatial techniques

RETRACTED ARTICLE: Spatial and temporal analysis of flood hazard assessment of Cuddalore District, Tamil Nadu, India. Using geospatial techniques

A multiscale analysis and classification of normalized difference vegetation index value method in Kannad Taluka, Aurangabad District, using remote sensing and GIS

Geomorphologic Change in Nagavali River Basin: Geospatial Approach

Contact Info

Product

Resources

About