Browsing by Author "Shetty, Amba"

Now showing 1 - 6 of 6

Assessment of Hydrological Impacts of Land Cover Changes and Climate Variability in the Geba Catchment, Ethiopia
(National Institute of Technology Karnataka, Surathkal, 2016) Hailu, Gebremedhin Kiros; Shetty, Amba; Nandagiri, Lakshman
Land use/land cover (LU/LC) and climate are the two main factors directly influencing catchment hydrological processes and consequently changes in these factors will result in significant hydrological impacts. Quantifying the magnitude and direction of these impacts is of great importance for land use planning and sustainable water resources management. The Geba catchment (5137 km2) located in the highlands of Northern Ethiopia; Africa contributes a significant portion of flow in the river Nile and forms an important source of water to a large population. In the past few decades, the catchment has experienced significant changes in LU/LC in the form of degradation due to anthropogenic activities and subsequent restoration brought about by conservation measures. Also, trend analysis of hydro-meteorological data carried out as part of this study provided evidence of changes in rainfall and temperature regimes in the catchment. Therefore, the present study was taken up to characterize the hydrology of the Geba catchment using available hydro-meteorological data and to apply and evaluate the potential of the Soil and Water Assessment Tool (SWAT) model to simulate major hydrological processes and sediment dynamics in the catchment. The objective was to use SWAT to simulate changes in hydrological processes brought about by changes in LU/LC and climate variability within the catchment. Accordingly, the research methodology adopted involved the following tasks: (1) Using historical (1971-2013) ground-based observations of rainfall, air temperature (7 climate stations) and streamflow (1 gauging station) statistical and trend analyses were carried out for monthly and seasonal time steps. Also, trends in several extreme climatic indices related to rainfall and temperature were analysed (2) LANDSAT satellite imagery acquired for multiple dates during the period 1971-2013 were subject to standard image processing and supervised classification procedures to derive LU/LC maps for the Geba catchment. These classified maps were used to detect changes in different LU/LC classesii during the periods 1973 – 1987, 1987 – 2000 and 2000 – 2013 (3) Using a variety of inputs (ground and satellite-based) related to topography, soils, LU/LC, rainfall and climatic variables, the ArcGIS version of the SWAT model (ArcSWAT) was applied to the Geba catchment. Given that the catchment experienced significant changes in LU/LC over the 40 year period considered, a novel model calibration/validation approach was adopted involving the use of different LU/LC maps for different time periods (4) Using observed streamflow records at the outlet of the Geba catchment, the SWAT model was subject to sensitivity analysis following which calibration and validation was carried out using both monthly and daily time steps. Model performance in simulating streamflow and sediment concentration at the outlet was evaluated using different statistical criteria (5) Using the validated SWAT model, a novel method to evaluate the separate and combined impacts of LU/LC changes and climate changes on major water balance components in the Geba catchment was implemented. Results of trend analysis revealed that during the study period (1971-2013), rainfall and streamflow exhibited a decreasing trend, while maximum daily air temperature had an increasing trend and minimum daily air temperature showed decreasing trend at 95 % confidence level. As regards LU/LC changes, during 1973–1987 and 1987–2000 time periods about 10.83 % and 9.13 % of the catchment area was transformed largely from shrub, forest and rangeland mainly to agriculture and barren land. During 2000–2013, about 18.37 % of the total catchment area was transformed from barren land and range to agriculture, shrub, forest and urban area. SWAT model validation using observed streamflow records yielded values of coefficient of determination (R2) between 0.86 and 0.96 and Nash-Sutcliffe efficiencies (ENS) between 0.73 and 0.83 for different simulation periods with a monthly time step. For daily streamflow predictions, R2 values ranged between 0.77 and 0.91 and ENS values were between 0.7 and 0.79. SWAT also provided reasonably accurate predictions of daily sediment concentrations during validation (R2: 0.81-0.895, ENS: 0.79-0.80). These results prove that the SWAT model is a reasonably accurate tool for simulation of hydrological processes in the Geba catchment, whereas R2iii and ENS for daily and monthly flow were very less (satisfactory) for the single static LU/LC (2000) map, mostly followed in many studies. Impacts of LU/LC changes and climate variability were evaluated by dividing the study period (1973-2013) into three phases based on LU/LC and climatic conditions: Phase (I) - LU/LC maps of 1973 and 1987, climate of 1974-1983 and 1984-1993 Phase (II) - LU/LC maps of 1987 and 2000, climate of 1984-1993 and 1994-2003 Phase (III) - LU/LC maps of 2000 and 2013, climate of 1994-2013 and 2004-2013. The SWAT model was run separately for four scenarios in each phase involving combinations of LU/LC and climate. Results indicated that the combined impacts of the LU/LC changes and climate variability increased streamflow and potential evapotranspiration in both Phases I and II, while available soil water contents decreased. Positive impacts in the form of reduced streamflow and increased soil moisture resulted in Phase III due to extensive conservation measures implemented after 2000. Overall, changes in LU/LC seemed to have a higher impact on hydrological processes than changes in climate. The present study has demonstrated the applicability and efficacy of a convenient methodology integrating satellite remote sensing and modelling to characterize hydrological processes and simulate hydrological changes in a heterogeneous tropical catchment. The proposed strategy may be adopted to formulate strategies for sustainable land and water resources management in the region, and in similar hydro-climatic settings elsewhere in Africa.
Hyperspectral Vegetation Indices for Arecanut Crop Monitoring
(National Institute of Technology Karnataka, Surathkal, 2017) B. E, Bhojaraja; Shetty, Amba; Nagaraj, M. K
Arecanut (Areca catechu L.) is one of the major profitable plantation crop grown in few regions of the World. Karnataka state in India produces almost half of the world’s total production, in that contribution from Shivamogga district and Coastal Karnataka is significant. The production per unit area in Karnataka is considerably less. The major reasons may be improper irrigation practices, poor soil maintenance, lack of technical knowledge on irrigation water quality, quantity, fertilizers used and frequent occurrence of diseases, small size and spatially scattered farms. These reasons were very typical in Chennagiri region of Karnataka. Farmers’ practice adding tank silt lifted from nearby tanks to their farms followed by drip irrigation in the form of flooding. In this region a typical disorder called crown choke harmed an adult plant’s life. The objective of this research is: to explore the potential of advanced tools for Arecanut crop monitoring and to demonstrate it on portion of Chennagiri region of Karnataka. Advanced technological tools used include GPS, Hyperspectral remote sensing data and GIS. Hyperspectral remote sensing is one of the fastest growing techniques in the field of remote sensing due to its vast applications with improved accuracy over conventional method. Spectral library was built separately for different age group and stressed crops using spectroradiometer. Care was taken to match field data with the Hyperion data acquisition time. Hyperion hyperspectral data was classified into stressed versus healthy and different age group crops using developed spectral library. Stressed versus healthy crop classification revealed 10% crops were under stress in patches. To find a scientific reason for crown choke disease affected crops inflated in study area, grid wise soil and water samples were collected, and subjected to standard physico-chemical analysis. Potential evapotranspiration (ETo) was computed using Normalized Difference Vegetation Index (NDVI) based crop coefficient (Kc) method due to non-availability of weather parameters. ETo, Integrated with Hargreaves Samani method was adopted to compute the crop water requirement of different age crops. Narrow bands in hyperspectral data facilitate computation of several spectral indices and can facilitate improved classification accuracy. Indices developed being Disease Index (DI) to identify disease severity in Arecanut crop, Age Index (AI) to segregate the Arecanut crops into different age groups and Arecanut Crop Water Requirement Index (ACWRI) was built to compute age based crop water requirement.ii Important wavelengths were identified among the hundreds of bands to compute the crop water requirement using statistical techniques. Stepwise Multi Linear Regression (SMLR), Partial Least Square Regression (PLSR), and Variable Importance for Projection (VIP) were the techniques of choice. These techniques also facilitated construction of simple models to predict the Arecanut crop water requirement. On the basis of diseased v/s healthy crop classification, it was inferred that more than 10% of plantation under study was affected by crown choke disease. The physico-chemical analysis revealed that improper soil management is the main cause for crown choke disorder. Soil characterization and water quality analysis infers soil is poorly graded (82% of silt content) with very low hydraulic conductivity of 3.2×10-7 cm/sec, and high bulk density of 2.12 g/cm3. This impervious nature caused water logging and lead to salinity. Age based classification results revealed Arecanut crop can be classified into different age groups; below 3 years, 5 to 7 years, 8 to 15 years and above 25 years. And within class classification accuracy of 72% was observed for Support Vector Machine (SVM) classification with linear kernel. Age based Arecanut crop water requirement map reveals that crop water requirement varies with age of the crop, below 7 years of crop it is 19 and for above 15 years it is 25 liter/day/plant. The derived ACWRI, DI, AI indices to monitor Arecanut crop ranges from 0 to 1 to indicate the age based crop water requirement, disease severity, and age of crop respectively. From the hyperspectral data significant wavelengths were identified: (i) to map the stressed Arecanut crops (750, 550 and 675nm), (ii) Arecanut crop age predication (540, 680 and 780nm). (iii) And to predict the age wise crop water requirement using statistical models: SMLR revealed that 681 and 721nm are significant. PLSR also in agreement with SMLR i.e 681,721 and 548nm are important. Whereas a VIP technique revealed wavelengths 1043, 1053, 1033, 1083, 1023, 1013, 1104, and 854nm are important. This study concludes that, hyperspectral remote sensing data processed with standard procedures with appropriate atmospheric corrections algorithms and integrated with field studies along with statistical models can be effectively used for Arecanut crop monitoring. This study also demonstrates that, how advanced technological tools can be used to address societal problems say crop monitoring. The output of the research is useful to the farming community to actively plan their agriculture water requirement, and also improves water use efficiency.
Integrated Surface Water Resource Modeling and Irrigation Productivity in Lower Baro, Ethiopia
(National Institute of Technology Karnataka, Surathkal, 2024) DENEKE, FISEHA BEFIKADU; Shetty, Amba; Fufa, Ing. Fekadu
The management of surface water resources is hampered in many river basins by a lack of data. The problem is for several of Ethiopia’s river basins increasing the productivity of surface irrigation and scientifically understanding the factors that led to integrated surface water modeling, particularly in Ethiopia's lower Baro is useful. The objectives of this study were (i) to review the land cover (LC) change implications to hydrological variables soil erodibility and yield reduction (ii) to explore statistical and trend analysis of hydrometeorological data, (iii) to quantify the surface water potential and irrigation water demand, and (iv) to investigate the satellite-ET based irrigation performance using Water Productivity Open-access Portal database and to come up with a strategy for quantifying the spatial and temporal increase water use efficiency (WUE) and system water use efficiency (sWUE) in the rainfed and irrigated area of lower Baro watershed. GIS-based multi-criteria evaluation used with the interaction of 8 factoring parameters, to see the low level of irrigation development. In the eight sub-classes, a total of 20, 325 km2 of appropriate pastoral land has been transformed into rainfed rice, sugarcane, maize, and vegetable land. This study used GIS, RS, Water Evaluation and Planning (WEAP), Cropwat8.0, and EasyFit software. The soil moisture rainfall-runoff method was computed using the WEAP hydrological model for the surface water demand and potential simultaneously from 2000-2014 and 2020-2030. This work used systematic reviews and a meta-analysis technique to examine the LC change and its effects on hydrological variables, soil erodibility, and yield reduction. Record identified through Scopus Searching, Web of Science Searches, and Google Scholar. Fully articles were assessed for eligibility and excluded for reasons. In the data search, 85 articles with investigations published between 2007 to 2022 were examined. Then, for surface water potential and irrigation productivity, only 2% of the abstracts that were eventually evaluated for assessment were selected. Four crops were selected to grow in these identified irrigable areas, and their gross irrigation demand was calculated using Cropwat8.0. In addition to annual streamflow variability, using graph pad prism 9.4 the monthly streamflow variability was determined. With the help of the WEAP system's parameter estimation tool weekly, average streamflow calibration was performed. II As a result, of the review, in the lower Baro, built-up/ settlement, agricultural land, water body, bare/ outcrop, and commercial farm rose roughly +195, +48, +35, +35, and +1%, respectively. On the other hand, shrubland, rangeland, forest land, and wetland decreased by 1, 0.5, 5, and 10%, respectively. But the revised universal soil loss equation looks to be a good alternative and soil water conservation measures are crucial for minimizing soil erodibility in lower Baro. As a result, of the water balance obtained the maximum estimated monthly hydropower potential, irrigation water demand, livestock water demand, and surface water potential were 60.3 Mm3 and the corresponding outflow value was 52.4 Mm3. The total estimated mean annual surface runoff leaving each station of the watershed was 462.06 Mm3. The coefficient of determination (R2) result was 0.88 and the Nash efficiency coefficient (NSE) was 0.91 highest at the Baro Gambella station. The anticipated irrigation requirement for the selected crop's driest five months of May, February, March, January, and April was 1, 0.9, 0.78, 0.78, and 0.34 l/s/h. The Baro Gambella sub-catchment had maximum critical values test results of σ = 12.6, μ =11.9, and γ = 0, while the Sor Metu showed the smallest value of 0.80, 1.75, and -0.03. Across the watershed, the sWUE varies with runoff, with a coefficient of variation of 71%. As a result, the overall accuracy of the LC change was 81%, the Landsat 8 images of the soiladjusted vegetation index showed a maximum value of 0.87 and a minimum of -1.5. The normalized vegetation index of 0.58 maximum and -1 minimum was observed. By 2050, the sWUE will be 10% lower temporally, but its spatial variability will be 25% higher. From 2017-2023 an increase in trees (dense forest), scrub/shrub land, flooded vegetation, and bare ground, while there had been a decline in water bodies and crops during the same period. When yield gaps are increased by a factor of 1/3, 2/3, and 3/4, the Baro Gambella sub-catchment has the biggest yield gaps 443.52, 887.04, and 1008.106 kg respectively, while the Gumero Gore sub-catchment experiences the smallest yield gaps 0.01, 0.02, and 0.03 kg respectively. As a result, the crop water productivity, ET, crop index, and temporal fluctuation of the yield gap were investigated. Also, the available dry river flow does not meet the available potential irrigable land. Moreover, to increase the irrigation crop water productivity by 2050 in the lower Baro watershed. Therefore, improve soil infiltration and water storage, which decreases runoff and the water lost by ET and raises sWUE.
MINERAL IDENTIFICATION On MARTIAN SURFACE USING SUPERVISED LEARNING APPROACH FROM CRISM HYPERSPECTRAL DATA
(National Institute of Technology Karnataka, Surathkal, 2024) KUMARI, PRIYANKA; Shetty, Amba; Koolagudi, Shashidhar G
The availability of spectral libraries for CRISM (Compact Reconnaissance Imaging Spectrometer for Mars) data through NASA’s Planetary Data System has revolutionized the study of the surface mineralogy of Mars. However, building supervised learning models for mineral mapping remains a challenge due to the scarcity of ground-truth training data. In this thesis, an innovative framework is presented that leverages supervised learning to classify spectra within CRISM hyperspectral images. To overcome the data limitation, an augmentation approach is employed that creates the training data by augmenting the minerals available in the MICA spectral library, preserving key absorption signatures of each mineral class while introducing adequate variability. The framework includes a comprehensive pre-processing pipeline, featuring a novel feature extraction method to capture distinctive absorption patterns in the spectra. The approach is validated using CRISM images from diverse Martian locations and interactive mineral maps are also provided for the detected dominant minerals. While this initial framework ensures acceptable accuracy, utilizing more sophisticated learning models and advanced preprocessing techniques can enhance the performance of the framework. Spectra in remotely sensed hyperspectral images are often affected by the presence of continuum, which changes the global curvature of the spectra, although the key absorption signatures are present. The continuum removal process, one of the critical preprocessing steps in the pipeline, is modified from the traditional approach to a novel method named Segmented Curve Fitting, which can identify more absorption shoulder points in a spectrum and thus can detect the absorption features in it more distinctively. Lastly, the thesis introduces MICAnet, a specialized Deep Convolutional Neural Network (DCNN) architecture tailored for mineral identification using CRISM hyperspectral data. Inspired by Inception-V3 and InceptionResnet-V1 architectures, MICAnet leverages 1-dimensional convolutions for processing spectra at the pixel level. This innovative architecture represents a significant contribution, being the first solely dedicated to this objective. The performance of the mineral mapping framework is assessed using both simulated data of varying complexity and a real CRISM TRDR/MTRDR hyperspectral dataset. In conclusion, this study advances the field of planetary science and remote sensing by providing automated approaches for mineral identification and mapping on Mars, also, enhances the understanding of Martian surface mineralogy, offering valuable insights into the planet’s geological history and habitability.
Novel Techniques in Hyperspectral Data Analysis for Endmember Extraction, Change Detection and Classification
(National Institute of Technology Karnataka, Surathkal, 2024) Yadav, Palla Parasuram; A. V. Narasimhadhan; B. S. Raghavendra; Shetty, Amba
Hyperspectral image (HSI) analysis is a powerful technique in remote sensing that involves the acquisition and analysis of images captured across hundreds or even thousands of narrow and contiguous spectral bands. Unlike traditional remote sensing techniques that capture information in just a few broadbands, HSI provides detailed spectral information for each pixel in an image scene. This wealth of spectral data enables a more comprehensive understanding of the Earth’s surface and the objects it contains. By analyzing the unique spectral signatures of different materials, HSI enables the identification and discrimination of various land cover types, vegetation species, soil properties, and even specific minerals. However, the analysis of hyperspectral data presents several challenges that require specialized approaches. Endmember extraction (EE) is one such challenge, involving the identification of pure spectral signatures or reference spectra that represent specific target materials. Spectral matching is a vital component of HSI analysis that involves measuring the degree of closeness between the spectral signatures extracted from the image and those obtained through ground-based spectrometer measurements or known reference spectra. Spectral matching algorithms are useful not only for validating the accuracy of image-based signatures but also for feature extraction. This matching process helps in the identification, analysis, and interpretation of different materials or targets present in the HSI. Through the combination of endmember extraction and spectral matching in HSI, diverse applications in geology and related fields are empowered, enabling tasks such as geological mapping, mineral exploration, environmental monitoring, and land cover analysis with increased accuracy and efficiency. Although hyperspectral imaging was originally developed for mining and geology, mineral identification using hyperspectral data has not been addressed adequately yet and remains a challenging task. HSIs due to advancements in spatial-spectral resolutions and the availability of multi-temporal information are in demand for many applications. Change detection (CD), in particular, is an important and challenging problem in monitoring changes such as deforestation, urban development, and landslides using time series HSI data. Though several endmember extraction algorithms (EEAs) are developed, spectral matching algorithms (SMAs) have not been explored much in the extraction of spectrally distinct signatures. Therefore, in this work, similarity measures based EEAs (SM-EEAs) are proposed to explore the fundamental characteristic, i.e. spectrally distinctive in nature, of endmembers. Experimental results on proposed EEAs i.e., a similarity measures-based subtractive clustering algorithm (SM-SCA) and a similarity measures-based endmember initialization algorithm (SM-EIA) showed the applicability of SMAs in extracting spectrally distinct signatures as the endmembers and also hinted the importance of endmember initialization. The darkest pixel identified as a target pixel of interest (TPOI) in the further investigation on endmember initialization strategies emerges not only as a potential TPOI but also contributes to improving the performance of EEAs when combined with the brightest pixel as TPOIs. Experiments carried out on an improved SM-EIA to test its applicability in extracting pure endmembers present maximin-distance algorithm (MDA) do not able to identify vertices of the simplex with simple metrics like Euclidean distance (ED) and other simple SMAS but with higher dimensionality metrics like volume. The proposed corner-driven iterative clustering algorithm (CDIC) appears to perform better in EE by identifying the corner pixels and thereby providing training samples for HSI classification. Though few already developed spectral matching measures are available, the identification of diagnostic features of spectrally distinct signatures with the existing SMAs to discriminate them effectively is still a challenging task. Therefore, this work presents a gradientbased spectral similarity measure (GSSM) that captures the diagnostic (absorption) features to measure the degree of closeness between spectral signatures. The effectiveness of the proposed GSSM in distinguishing spectrally distinct signatures is studied with that of other spectral matching algorithms in (i) discriminating endmember signatures (ii) mixed pixel identification (iii) clustering spectral signatures of different classes and (iv) endmember extraction. The proposed GSSM was not only able to highlight diagnostic features of target signatures but also showed its effectiveness in discriminating spectrally distinct target signatures better than other SMAs. Further study on gradient correlation (GC) incorporated showed improved discrimination power with geometrical SMAs. Further, a meaningful way of measuring RSDPW is proposed. Reformulated RSDPW appears to be more meaningful in discriminating endmembers and obtaining the range of RSDPW values for different levels of discrimination than the former one. The high dimensionality of HSI data and limited availability of hyperspectral CD data sets with ground-truth change map make CD not so easy but a difficult task. Though there are many classical and deep learning (DL) based algorithms to detect changes, either their performance is not so better or the final performance depends on efficiency of pre-detection algorithms. In addition, there is not much comprehensive study on developing CD algorithms that not only simple to use but also as efficient as that of DL based algorithms is available. Therefore, an endmember related feature extraction is proposed for HSI-CD. Proposed ATGP based CD algorithms not only perform better than classical CD algorithms but also able to reach the performance of DL based CD algorithms. additionally, even a minimum number of features around three to five (3-5) also good enough to get high accuracy as that of DL models. Mineral identification remains a challenging task due to the subtle differences among the spectral signatures of minerals and insufficient ground truth. The classical spectral angle measure (SAM) classifier is a simple model and does not yield high accuracy and an expert system for hyperspectral data classification (ExHype) is a binary classifier and therefore complex to train binary classifier modules equal to the number of minerals to be classified and obtain thresholds to gain accuracy. Due to lack of training samples and sufficient data with ground truth to be tested, DL models have not been explored much in mineral classification so far. To overcome this, a virtual sample generation to be able to generate more training samples that provide a chance to explore DL models that need variations in training samples in mineral classification is proposed. Further, a one-dimensional convolutional neural network (1-D CNN) model, trained on training samples generated by virtual sample generation, designed to classify minerals performed well in classifying the tested mineral classes with high accuracy.
Surface Soil Moisture Retrieval over Heterogeneous Agricultural Plots Using Sar Observations
(National Institute Of Technology Karnataka Surathkal, 2023) G, Punithraj; U, Pruthviraj; Shetty, Amba
Soil moisture is a basic component of meteorological cycle and in the determination of agricultural crop yield. Spatial information about soil moisture over agricultural crops is required for efficient irrigation, which in turn helps in saving water and increases the crop yield. However, capturing spatiotemporal field measurement of soil moisture is time consuming and not a practical approach. Synthetic Aperture Radar (SAR) remote sensing is a valuable tool for retrieving surface soil moisture over agricultural fields owing to its great sensitivity to surface soil moisture. The objective of the research is retrieval surface soil moisture over typical heterogeneous agricultural plots of a semi-arid region of India using C and L band polarized SAR data. A methodology is developed to retrieve surface soil moisture over different agricultural fields at different crop stages. To implement the methodology, a typical agriculture-dominated landscape has been selected. For the study, different agricultural plots of Malavalli village in Karnataka, were selected. Agricultural crops include; crops like Paddy, Tomato, Maize, Sugarcane and a reference bare field. Agricultural plots of size 1 acre approximately, were selected and sampling grids were made according to SAR ground resolutions. Field measured data like surface soil moisture, surface roughness, soil texture, vegetation height and vegetation water content were collected from every grid of the agricultural plots in synchronization with satellite pass. Sentinel-1a, C-band data and ALOS PALSAR-2, L-band SAR data products are used to retrieve surface soil moisture. The developed models were compared with existing models and validated using field measure values. Surface soil moisture was retrieved using L-band SAR across agricultural plots at two distinct crop stages. Initially, processed SAR images are decomposed using Freeman Durden, Yamaguchi and Van-Zyl decomposition techniques to know the major scattering components (like surface, dihedral, and volume scattering). In vegetative crop stage, surface scattering (>34%) is dominating scattering component, which shows less interaction of vegetation with radar backscattering energy. iSurface scattering component of Yamaguchi decomposition has dependence on field measured surface soil moisture with R2> 0.5 good correlation. Multilinear regression (MLR) is carried out in which soil moisture (Mv) is a dependent variable and 𝑠𝑢𝑟𝑓𝑎𝑐𝑒 , 𝑉𝐻−𝑉𝑉 and 𝐷𝑖ℎ𝑒𝑑𝑟𝑎𝑙 are considered as independent variables and validated. To assess the resilience of the developed models, it is compared with existing models like Oh 1992, Oh 2004, X-Bragg and WCM. RMSE of developed model varies from 0.82 to 2.51 cm3/ cm3 for two distinct crop stages. Whereas, in case of sugarcane at grand growing stage none of models performed well (RMSE= 3.644.7 % gm/ cm3). X-Bragg model is underestimating surface soil moisture in two distinct crop stages of paddy, maize, tomato and sugarcane field plots (RMSE= 1.214.23 % gm/ cm3). In the same way, surface soil moisture is retrieved using C-band SAR across above mentioned agricultural plots for whole crop cycle of each crop at an interval of 12 days. Each crop cycle is divided into vegetative, maturity, yield formation stage and surface soil moisture of each crop stage is estimated. The relationship between backscattered energy and soil moisture, roughness and vegetation parameter (RVI) is analyzed and MLR analysis is carried out to develop semi empirical model (SEM) and validated against grid sampled field data (RMSE= 1.38.1 % gm/cm3). The developed model found to be better when compared with Oh model, 1994. In grand growing stage of sugarcane and yield formation stage of maize and sugarcane, the RMSE values were found to 4.18.1 % gm/cm3. Which shows the vegetation attenuation increased as the crop matures and affecting soil moisture retrieval beneath it. Performance of C-band dual polarized data with L-band quad polarized data at two different crop stages were compared for surface soil moisture retrieval. Quad polarized data is found to performing better than dual polarized data. At various crop stages, the proposed semi-empirical model for retrieving surface soil moisture functions effectively. In future, the developed model can be simplified by introducing constant parameters based on crop stage and type of crop. This study helps to understand the spatial variation of soil moisture within the small plots thus helping marginal farmers and local irrigation departments for better allocation of water resources.