Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
6 results
Search Results
Item Temporal crop monitoring with sentinel-1 sar data(Springer Science and Business Media Deutschland GmbH, 2021) Salma, S.; Dodamani, B.M.Spatial and temporal analysis of crops and other land surface features is the major application of the present spaceborne sensors. Among most of the spaceborne sensors, synthetic aperture radar (SAR) is having the advantage of all-weather capability with low-frequency bands. SAR data is useful for decompositions, crop classifications, etc. In this study, paddy fields are classified using Sentinel-1 ground range detection. Synthetic aperture radar data with the combination of vertical polarization with the horizontal receiver (VV and VH) is selected for the temporal variation analysis and classification analysis of paddy fields along with the plantations. Multi-temporal classification analysis is done using random forest classifier, and correlation obtained is 0.78 and 0.45 in VH and VV polarization, respectively, and the error rate shows significant variation in both the polarizations, i.e., 0.05 and 0.25 (in VH and VV polarizations, respectively), which indicates more error rate in VV polarization band. In this study area, VH polarization shows better classification and correlation compared to VV polarization due to double bounce effect of urban features, paddy and plantation at the stem elongation and booting stage in VV polarization. © Springer Nature Singapore Pte Ltd 2021.Item Identifying Rice Crop Flooding Patterns Using Sentinel-1 SAR Data(Springer, 2022) Keerthana, N.; Salma, S.; Dodamani, B.M.In India, the majority of the population relies heavily on rice as it is their primary source of nutrition. Rice crop yield productivity depends on seasonal variations and mainly depends on hydrological conditions. Long-term water clogging in rice fields for an extended period causes crop flooding and reduces production in terms of quality and quantity. This study deals with the identification of rice crop fields and their flooding due to surface irrigation using Sentinel-1 SAR data. The identification of rice fields was attempted by classifying the image data using a random forest algorithm. For crop flooding analysis, the temporal backscatter of the corresponding fields has been extracted from SAR data and local thresholding is used. The temporal analysis of the SAR backscattering showed a similar tendency in terms of crop growth. The overall accuracy of rice crop classification for VH and VV is 97.30% and 92.24% with RMSE errors of 0.0143 and 0.0145, respectively, obtained at the peak stage of the crop. From the crop flooding analysis, it is observed that crop fields have been flooded at the growth stage due to surface irrigation and rainfall. We identified crop flooding even at the crop mature stage. In the analysis, it has been observed that the flooding is not due to irrigation water but is due to the precipitation water. © 2022, Indian Society of Remote Sensing.Item Target decomposition using dual-polarization sentinel-1 SAR data: Study on crop growth analysis(Elsevier B.V., 2022) Salma, S.; Keerthana, N.; Dodamani, B.M.Decomposition of synthetic aperture radar data has been carried out using fully polarised microwave bands. Considering the economical point of view, fully polarimetric SAR data is expensive to use for many applications like soil and agriculture, where, it is important to monitor frequently. With the advancement of human civilization, new agricultural techniques and crops are being developed to meet global food demand. With the development of crop growth, crop texture and dielectric properties varies, which is depicted in the backscattering values along with the crop growth. In this study, Sentinel-1 SAR data is used, which is freely available in dual polarimetric mode with a temporal revisit of 12 days with respect to the transmitter polarizations. In this work, we attempt to decompose the targets from dual polarised SAR data using entropy and alpha bands of H-A-α decomposition. The entropy and alpha band clusters are obtained by using K-means unsupervised classification is utilized for target decomposition. The clustering process is repeated 30 times for 100 iterations to obtain the optimum grouping of pixels. The clusters are plotted on the H-α plane to get an H-α plot of dual-polarization SAR data for target decomposition. The obtained H-α plot is used to identify the crop stages and its scattering mechanism at different growth stages. Crops grown in selected crop fields during the considered period include ginger, tobacco, rice, cabbage, and pumpkin. An attempt is made by plotting the time-series trends of early and late-planted crops with peak mature stages in terms of backscattering analysis, and the results were compared to the H-α plot to gain a better understanding of crop growth scattering mechanisms at various growth stages. Although the backscattering values for the VH and VV polarizations of crops are different, the temporal backscattering study showed the same trend for both polarizations with good similarity of VH polarization than VV for analyzing crop growth stages. The crop growth scattering mechanism on the H-α plane produced similar results to the temporal analysis. © 2022 Elsevier B.V.Item Identifying Municipal Solid Waste Dumping Site Location Using AHP and GIS Techniques: A Case Study of Coimbatore District, India(Springer, 2022) Aishwarya, V.; Salma, S.; Dodamani, B.M.Increased municipal solid waste generation in urban areas is a result of fast population growth and urbanization. Dumping or landfilling in unsuitable areas becomes the biggest concern for solid waste management authorities. The present dump yard at Vellalore, Coimbatore district, affect nearby settlements with a foul stench and flying ashes due to strong winds. The study’s main goal was to provide alternative landfilling sites in the Coimbatore district using GIS and analytic hierarchy process (AHP) techniques. Nine criteria were considered. These were population density, slope, geology, geomorphology, land use/land cover, and proximity to road, river, railway, and airport. Weighted overlay, a spatial analyst tool that reclassifies raster maps and a final suitability map, is generated. According to the findings, the possible landfill zones were found in the northeastern region of Coimbatore. Hence, the environmentally suitable sites can be selected by using remote sensing and GIS techniques. © 2022, Indian Society of Remote Sensing.Item An optimum datasets analysis for monitoring crops using remotely sensed Sentinel-1A SAR data(Taylor and Francis Ltd., 2023) Salma, S.; Keerthana, N.; Dodamani, B.M.To effectively monitor crops, it is necessary to select extremely redundant satellite images and to know the number of acquisitions required for a specific period to analyse cropping patterns, thereby reducing analysis time. In this paper, we have examined an empirical analysis for the optimum dataset (OptD) selection required to monitor the crops. Sentinel-1 dual-polarized SAR datasets were used in this study to illustrate the effectiveness of optimum datasets required for the considered crops (ginger, tobacco, rice, cabbage, and pumpkin). In this work, at first, the entropy and alpha bands were treated as cluster centres for crop decomposition and its scattering mechanism using the cluster-based K-means unsupervised classification technique. The clusters are plotted on the H-α plane to get the H-α plot of dual-polarization SAR data for target decomposition. To understand the dominance of scattering type with crop growth stage, the obtained scattering distribution from the H-alpha plot is scaled to a percentage analysis. Based on qualitative observations of the percent scattering distribution of crop pixels over a h-alpha plot and backscattering coefficient behaviour at different crop growth stages, an empirical approach has been used to select dataset reduction. It has been suggested that the combination of successive repeated data with similar scattering analysis of combined h-alpha plots and backscattering analysis is the best reduced dataset selection for effective crop monitoring. From the analysis, the optimum dataset required for monitoring Ginger (from the flourishing stage), Tobacco, Paddy, Cabbage, and Pumpkin has been identified, and found that the tobacco crop requires fewer datasets, whereas the rice crop requires a greater number of datasets for monitoring. Despite the challenges associated with, p-bias for the crops was achieved at good levels, given that, lowering the datasets to obtain the optimal number without significantly reducing the accuracy of the data. © 2023 Informa UK Limited, trading as Taylor & Francis Group.Item Analysis of RVI for rice crops in small-scale agricultural fields using Sentinel-1 SAR data: case study on LAI retrieval using regression algorithms(Springer Science and Business Media Deutschland GmbH, 2025) Salma, S.; Ket, S.K.; Dodamani, B.M.Leaf Area Index (LAI) is a crucial indicator for assessing plant growth, canopy structure, photosynthetic capacity, and overall productivity. The Radar Vegetation Index (RVI), a well-established microwave metric, serves as an effective tool for retrieving the LAI due to its sensitivity to vegetation characteristics. The primary objective of utilizing RVI in LAI studies is to improve the accuracy and reliability of LAI estimation, where optical methods may be hindered by atmospheric conditions. Over the past decade, numerous studies have explored the relationship between RVI and LAI, highlighting the potential of RVI for accurate LAI estimation in crops. In particular, for rice crop analysis in this study, the RVI is derived by incorporating the Degree of Polarization (DOP) from a 2 × 2 covariance matrix as the coefficient, along with the polarization backscatter of Sentinel-1 C-band Synthetic Aperture Radar (SAR) data. The study also explores RVI derivation from M-chi (m-?) and M-delta (m-?) decomposition (assuming circularity in dual-polarized data) and linear backscattering intensities. Using the RVI’s, machine learning regression models are applied to retrieve LAI. The DOP over crop period, the temporal analysis of RVI, and in-situ LAI has been employed to examine trends during crop growth. Notably, among all derived RVIs, the one obtained using the DOP technique, particularly when combined with random forest regression, consistently exhibits superior performance for rice crop LAI estimation (R = 0.91; RMSE = 0.25 m2/m2), whereas, the R value for other models ranges a lower value of 0.63 to a higher value of 0.83 with RMSE of higher value 0.64 m2/m2 to a lower value of 0.32 m2/m2. The findings in the study highlights the sensitivity of SAR data to the DOP and the vegetation structure of rice crops in small-scale agricultural fields. © The Author(s), under exclusive licence to the International Society of Paddy and Water Environment Engineering 2024.