Suryakant Sawant | IIT Bombay (original) (raw)

Papers by Suryakant Sawant

Environmental Monitoring and Assessment

MODIS observations on active fire events were obtained from Visible Infrared Imaging Radiometer S... more MODIS observations on active fire events were obtained from Visible Infrared Imaging Radiometer Suite (VIIRS). The burning of crop stubble increased NO 2 emissions by 22 to 80%. CO levels, on the other hand, have risen by 7 to 25%. A considerable variation in AOD was reported, ranging from 1 to 426%.

Sentinel-1-derived coherence time-series for crop monitoring in Indian agriculture region

Geocarto International

Integration of Sentinel 1 and 2 Observations for Mapping Early and Late Sowing of Soybean and Cotton Crop Using Deep Learning

IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium, 2020

The main objective of this paper is mapping of Soybean and Cotton crop area using the integration... more The main objective of this paper is mapping of Soybean and Cotton crop area using the integration of Sentinel-1 and 2 observations and Deep Neural Networks (DNN). The present research also attempted the identification of early and late sowing of Soybean and Cotton using time-series of Normalized Difference Vegetation Index (NDVI) and VH backscatter. The study was carried out in Wardha district of Maharashtra, India during Kharif 2019. The Sentinel-1 observations available during 15 Jun. to 30 Nov. 2019 and Sentinel-2 maximum NDVI and Normalized Difference Water Index (NDWI) composites during Aug. to Sept. and Oct. to Nov. 2019 were used for Cotton and Soybean area mapping. We evaluated the performance of tuned Random Forest (RF) and DNN for classification of Soybean and Cotton. Results showed that DNN performs better with an overall accuracy of 89.15% and the F-score of 0.856. Further, identification of early and late sown Soybean and Cotton was performed using short time-series of ...

Monitoring and Analysis of Viirs Fire Events Data Over Indian States of Punjab and Haryana

IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium, 2020

Paddy residue burning is common across Indo-Gagantic plane i.e. Punjab and Haryana states of Indi... more Paddy residue burning is common across Indo-Gagantic plane i.e. Punjab and Haryana states of India. Rice-Wheat cropping system is intensively followed across the Punjab and Haryana. Every year, Rice is cultivated from May to Oct. followed by the Wheat from Nov. to April. Most of the farmers burn the leftover plant debris after Rice harvesting and clear the fields for the next cropping season. The burning of crop residues releases several particles and gases into the atmosphere which causes huge air-pollution. There is an urgent need to monitor such man-made burning to avoid/minimize the air-water pollution. Satellites such as MODIS and VIIRS provide active fire events data daily. We have attempted to analyze the data provided by VIIRS over Punjab and Haryana. This paper attempts to answer a few research questions such as 1. How are the state and zone-wise trend in active fire events cropping seasons of 2017, 2018, and 2019, 2. When is the peak burning period across Punjab and Haryan...

Iot Based Automatic Drip Irrigation System

Irrigation is heart of agriculture, and is used to assist growing crops in the fields during the ... more Irrigation is heart of agriculture, and is used to assist growing crops in the fields during the inadequate rainfall period. Irrigation is one of the areas in agriculture domain where Information, communication and dissemination technologies (ICDTs) can be employed to open up new exciting directions for research and business [1]. Drip irrigation in particular has the potential to change the way the farms are irrigated if employed with ICDTs [2]. For this purpose design and development of IoT middleware for remote, anytime monitoring and management of smart drip irrigation system is proposed. The system calculates the crop water requirement for the farm based on soil moisture, humidity and other sensor values. These values are used to decide and control the amount of water required to supply through valves and then to drippers. The smart automatic drip irrigation system based on Internet of Things is a new mode to ensure smart farming practices for irrigation purpose. Drip irrigation...

Spatialization of rice crop yield using Sentinel-1 SAR and Oryza Crop Growth Simulation Model

2019 8th International Conference on Agro-Geoinformatics (Agro-Geoinformatics), 2019

Rice is a staple food across the majority of the world’s population that is expected to exceed 9 ... more Rice is a staple food across the majority of the world’s population that is expected to exceed 9 billion by 2050 and will require approximately 60% more food. In season and accurate information on the spatiotemporal distribution of rice cultivation, phenology across the region and spatial distribution of yield is of significant importance. This information is used by various stakeholders such as government, policymakers, insurance companies, and agri-input companies. Methods involving manual surveys for developing spatial crop yield are constrained by short harvest window and availability of the skilled human resource. Estimation of regional crop yield with precision and accuracy requires the use of high-resolution remote sensing data. The key contribution of this study is the spatial estimation of rice yield by assimilation of parameters derived from Synthetic Aperture RADAR (SAR) data from Sentinel-1 satellite into a process-based Oryza crop growth simulation model. The study has ...

Temporal Detection of Pesticide Residues in Tea Leaves Using Hyperspectral Sensing

IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium, 2019

Tea is considered as a healthy beverage due its antioxidant properties and resultant beneficial e... more Tea is considered as a healthy beverage due its antioxidant properties and resultant beneficial effects on human health. India is the second largest producer of tea in the world after China, but every year Tea plants are attacked by several pests and diseases that are responsible for 7-10% loss of the crop. Tea growers spray pesticides on the plants for better control on the pests and to reduce crop loss. The uncontrolled usage of pesticide with ineffective management practices results in high residue levels that are hazardous to human health. In this paper, an attempt has been made to detect the pesticide residue on the tea leaves using hyperspectral sensing. The data on leaves treated with three banned chemicals (Acetamiprid, Cypermethrin and Monocrotophos) and control healthy leaves was collected using spectroradiometer in the spectral range of 350-1052 nm in 213 narrow contiguous bands. The spectral observations of the leaf samples (total of 389 samples) in control and treated w...

Accurate and reliable information on spatio-temporal extent of surface water is critical for vari... more Accurate and reliable information on spatio-temporal extent of surface water is critical for various agriculture/environmental applications such as drought, flood monitoring, and understanding the availability of surface water for irrigation. Remote sensing (Optical as well as SAR) datasets are extremely useful to monitor sur- face water at massive scale. In monsoon months the optical remote sensing observations over semi-arid Indian sub-continent are obstructed due to cloud cover. Synthetic Aperture Radar (SAR) is a useful alternative for year-round monitoring of the surface water bodies. Sentinel-1A and 1B are very useful to monitor the changes at very high spatial resolution and frequently due to its high spatiotemporal resolution. The main objective is to establish an operational methodology for estimation of spatiotemporal variations in the surface water availability using Sentinel-1A and 1B observations. The study has been carried out in four districts of Coastal Andhra Prades...

Towards Internet of Things Based Approach for Using Archives of Earth Observation for Crop Water Management in Semi-Arid Areas

Climate change has huge impact on socio-economic and natural systems of semi-arid areas. Vegetati... more Climate change has huge impact on socio-economic and natural systems of semi-arid areas. Vegetation dynamics plays a crucial role in natural resources and land use planning and regional policy decisions. Increasing remote sensing platforms like satellites, airborne surveys, unmanned aerial vehicles, etc. facilitate the collection of spatiotemporal earth observations. The main objective of this study is to improve processing capabilities of proximal wireless sensing systems for crop water management in semi-arid areas. Methodology is proposed comprising of estimation of phenological stages of major Land Use / Land Cover (LU/LC) (i.e. forest, scrub forest and agriculture) in semi-arid region using multi-sensor (Landsat 7 and 8) remote sensing time series observations. A study area from semi-arid region of central India is selected to study the vegetation growth stages. In this study freely available noncommercial satellite imagery store Google Earth Engine (GEE) is used to extract the...

Towards using vegetation greening and browning patterns obtained from time series of remote sensing observations for irrigation water management

Remote Sensing for Agriculture, Ecosystems, and Hydrology XXI

Erratic rainfall with varying intensity and duration has raised the risks of crop failure in semi... more Erratic rainfall with varying intensity and duration has raised the risks of crop failure in semi-arid areas of south and south-east Asia. In subsistence irrigation cropping systems often it’s difficult to schedule the irrigation, i.e. when and how much water to irrigate. Therefore there is a need for a regional real / near real-time updated database on vegetation greening and browning to facilitate the irrigation scheduling decisions. With the advent of open archives of remote sensing from United States Geological Survey (USGS) and European Space Agency (ESA) have proven a unique set of long-term historical and near real-time observations. In this study, an attempt has been made to understand the vegetation greening and browning patterns using time series of remote sensing observations for irrigation water management. The main objective is to study the greening and browning of natural vegetation (i.e., grasslands and forests) and agricultural areas of Indian sub-continent for understanding the breaks in the rainfall spells and integrated approach for irrigation scheduling. The time series of vegetation indices have been extracted for predefined grid locations from Sentinel 2 remote sensing sensor. Further, an algorithm based on time series analysis were evaluated for estimating the vegetation growth stages. The estimated vegetation growth stages was compared with the agro-climatic zones. A methodology for subsistence irrigation scheduling has been proposed based on regional vegetation growth stages (i.e. onset, peak and end of the season). The estimated vegetation growth stages showed poor alignment with the agro-climatic zones. The integrated approach based on vegetation growth stages is promising for scheduling subsistence irrigation. The proposed methodology for vegetation growth stage identification has potential applications in drought risk assessment and in establishing key indicators for agro-climatic zones.

Investigating the Performance of Hyperspectral and Simulated Sentinel-2 Data for Soybean Canopy Nitrogen Estimation

2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS

Nitrogen (N) is one of the key nutrient element needed for optimum crop growth and production. De... more Nitrogen (N) is one of the key nutrient element needed for optimum crop growth and production. Deficiency of N leads to a decrease in crop production and excess results in poor root growth and leaching into groundwater thereby causing environmental issues. Hence the optimum application of N is needed which is possible by exactly estimating the available quantities of N in the plant. In this study, an attempt has been made to estimate N in Soybean leaves using the hyperspectral and simulated Sentinel-2 observations. Spectral observations of fifteen soybean leaf samples were collected using the EKO MS-720 Spectroradiometer. The instrument operates in the spectral range of 350–1050 nm. and collects data in contiguous 213 bands. Support Vector Regression-based models were evaluated using three feature selection methods, 1) individual hyperspectral bands, 2) Normalized band ratio's and 3) simulated Sentinel-2 bands and indices. Model performance was evaluated using R2. Analysis carried out using the individual hyperspectral bands showed that bands from the red and red-edge region are performing best with R2 between 0.872 and 0.876. However, NBR's estimated from band combinations in the red-edge region are performing best with R2 between 0.938 - 0.956. Further, we identified a subset of wavelengths to simulate Sentinel-2 spectral bands, results showed that red-edge and narrow NIR bands provide the highest R2 between 0.878 and 0.893. We observed that indices such as Canopy Chlorophyll Content Index (CCCI) and Chlorophyll Index Red Edge (CIRE) are performing better for N estimation with R2 of 0.946, 0.923, respectively. Based on the observations we can conclude that red, red-edge and narrow NIR region is useful for Soybean N estimation.

Assessing InSAR Coherence for Quantification of Agriculture Area Affected by Rainfall Events in Gujrat, India

2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS

In the present study, InSAR coherence products extracted from Sentinel-1 were used for the quanti... more In the present study, InSAR coherence products extracted from Sentinel-1 were used for the quantification of the agricultural region affected by normal to large excess rainfall events that occurred in the districts of Gujrat, India in July and August 2020. In this analysis, the coherence values retrieved during co-event (i.e. during rainfall) were comparatively found lower than the pre-event (i.e. before rainfall) for all the sub-divisions of the districts. Here, the pre-event and co-event coherence histograms were drawn and their point of intersection was used to determine an optimal threshold value for coherence below which agriculture area was considered as affected due to rainfall. More than 80 % of the total study area was found affected due to rainfall events. The obtained outcomes were crossexamined with the Landsat-8 images obtained for the study duration and the results were found encouraging.

Near Real Time Crop Loss Estimation using Remote Sensing Observations

2019 8th International Conference on Agro-Geoinformatics (Agro-Geoinformatics)

Natural calamities triggered by erratic weather conditions like cyclone, earthquakes, hail storms... more Natural calamities triggered by erratic weather conditions like cyclone, earthquakes, hail storms, and flood incurs substantial loss to the infrastructure and crops of the region. Countries across the globe are prone to such natural calamities. In India, specifically coastal parts are vulnerable to tropical cyclones. In 2018 east coast districts of Tamil Nadu and Andhra Pradesh, India were affected by the three cyclones namely Titli (11 Oct. 2018), Gaja (16 Nov. 2018) and Pethai (17 Dec. 2018) causing severe damage to seasonal crops such as Rice, Coconut and Areca Nut plantations. Traditional survey-based methods of crop loss assessment are time-consuming and labor-intensive.This study addresses the problem of near-real-time qualitative crop loss assessment due to tropical Gaja cyclone using the temporal data from Sentinel 1 and 2 satellites. The crop damage assessment study has been undertaken for Gaja cyclone in the affected district of Thanjavur, Tamil Nadu, India. The major crops cultivated in the district are Kharif Rice (locally called as Samba and Late Samba) and Coconut plantations. The study addresses qualitative loss assessment in terms of crop area affected. As a first step, we used time series data of Sentinel1 (VV and VH backscatter) available between Aug.-Nov. 2018 to map the Kharif rice area. Also, cloud-free Sentinel 2 scenes available during Mar.-May. 2018 have been used to map the Coconut area. Field visits were conducted to collect the geo-tagged plot boundaries for the rice crop and coconut plantations. The data collected through field visits was used both for model training and crop loss assessment. Google maps satellite layer was used as a base map for identification of other non-crop classes (i.e., forest, water, settlement, etc.). The overall accuracy of crop area classification was 87.23% for rice and 92.22% for coconut.Further, to estimate the crop loss, crop layers along with the NDVI were considered. Two crop loss scenarios, namely minimum damage and maximum damage, were identified for both the crops. The mean NDVI composite before the event, i.e., 1-15 Nov. 2018 was considered as the base. In case of maximum loss scenario, short term NDVI composite available immediately after the event, i.e., 17-25 Nov. 2018 was selected. After the cyclone, long term NDVI composite of the mean (i.e., 17 Nov.13 Dec. 2018) was used to assess the minimum loss scenario. Using field observations, the crop loss was categorized as severe loss, medium loss, low loss, and no loss. Results showed that the coconut plantations in Pattukkottai, Peravurani, and Papanasam blocks of Tanjavur are affected by the cyclone. The significant rice crop loss has been observed in Thanjavur, Orattanadu, Pattukkottai blocks. We have found the remote sensing based crop loss observations are matching with the government reports based on field observations. The remote sensing observations with human participatory sensing (i.e., field observations) has the potential for near-real-time crop loss assessment.

2021 9th International Conference on Agro-Geoinformatics (Agro-Geoinformatics)

The main objective of this study is the assessment of simulated Sentinel-2 data for bare surface ... more The main objective of this study is the assessment of simulated Sentinel-2 data for bare surface soil moisture estimation. Hyperspectral soil moisture data provided by in the spectral range of 450-950 nm over test site at Germany has been utilized in the study. Simulation of 8 bands (B2-B8A) of Sentinel-2 covering the same spectral range as that of hyperspectral camera was carried out using spectral response curve of Sentinel-2. Random Forest Regression based model was developed using all bands. Morover, important features were selected based on %IncMSE. Selected bands include B2, B4, B5 and B7. Evaluation of models developed using all the 8 bands and selected bands was carried out using the testing data. Root Mean Square Error of 1.0180 and R 2 value of 0.9131 was achieved for a model with 8 bands. However, RMSE was reduced to 0.9661 and R 2 was increased to 0.9357 in case of selected 4 bands. Moreover, validation of models developed on simulated data was carried out using Sentinel-2 satellite observations on demo farm, Pune India. Difference between actual and estimated soil moisture was found to be between -2.10 to 3.18.

Field Boundary Identification using Convolutional Neural Network and GIS on High Resolution Satellite Observations

2021 9th International Conference on Agro-Geoinformatics (Agro-Geoinformatics)

With advent of constellation of high-resolution micro satellites, the acquisition rate of earth o... more With advent of constellation of high-resolution micro satellites, the acquisition rate of earth observation has surpassed the rate of data processing. In semi-arid rainfed agricultural ecosystems area under crop varies across seasons. Due to small land holdings it’s often difficult to identify the field level crop cultivation information. Also, field boundaries are important for identification of crop extent, crop insurance, crop loan, carbon credit and to establish the credit score for the farm. Studies have reported effective edge detection using Deep Learning based classifiers. Geographic Information System (GIS) based topology operations for vector geometry are effective in correction of vector geometries. This study describes field boundary identification approach using Convolutional Neural Network (CNN) on high resolution satellite observations. A Holistically-nested Edge Detection algorithm is used to identify the edge raster images. The pixel error rate of 19% was obtained with 200 epochs and 131 training images. Finally, the edge raster images were geo-referenced and converted into vector polygon geometry. Topology operations such as sliver polygon removal, overshoot and undershoot error removal were applied to refine the field boundary output. The accuracy assessment of identified field boundaries was performed with manually drawn field boundaries. Key features such as area of the polygon and centroid shift were compared between actual and identified field boundaries. We observed mean of difference in area of 216 sq. meter and chentroid shift of 1.12 meter. We plan to train proposed architecture for different spatial resolutions and cropping conditions. Additional GIS based accuracy matrices like percent overlap will be used during the operational use.

A data-driven approach for bare surface soil moisture estimation using Sentinel-1 SAR data and ground observations

Geocarto International

Soil moisture is an important variable in the agriculture system. Likewise, accurate information ... more Soil moisture is an important variable in the agriculture system. Likewise, accurate information on soil moisture is needed for the effective modeling of many hydrological and climatological proces...

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences

The rise in global population has increased food and water demand thereby causing excessive press... more The rise in global population has increased food and water demand thereby causing excessive pressure on existing resources. In developing countries with fragmented land holdings there exists constant pressure on available water and land resources. Obtaining field scale crop specific information is challenging task. Advent of open freely available multi-temporal remote sensing observations with improved radiometric resolution the possibilities for near real / real time applications has increased. In this study and an attempt has been made to establish operational model for field level crop growth monitoring using integrated approach of crowd sourcing and time series of remote sensing observations. The time series of Sentinel 2 (A and B) satellite has been used to estimate crop growth related components such as vegetation indices and crop growth stage and crop phenology. In initial stage high valued cereal crop Wheat has been selected. The field level information (i.e. 108 Wheat fields) collected using mobile based agro-advisory platform mKRISHI® has been used to extract time series of Sentinel 2 observations (44 scenes for year 2016 and 2018). The moving average has been used for filling gaps in the time series of vegetation indices. The BFAST and GreenBrown package in R were used for detecting breaks in vegetation index time series and estimating crop growth stages. Analysis shows that the estimated crop phenology parameters were in better agreement with the field observations. In future more crops from different agro-climatic conditions will be considered for providing field level crop management advisory.

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences

Spatio-temporal crop phenological information helps in understanding trends in food supply, plann... more Spatio-temporal crop phenological information helps in understanding trends in food supply, planning of seed/fertilizer inputs, etc. in a region. Rice is one of the major food sources for many regions of the world especially in monsoon Asia and accounts for more than 11% of the global cropland. Accurate, on-time and early information on spatial distribution of rice would be useful for stakeholders (cultivators, fertilizer/pesticide manufacturers and agriculture extension agencies) to effectively plan supply of inputs, market activities. Also, government agencies can plan and formulate policies regarding food security. Conventional methods involves manual surveying for developing spatio-temporal crop datasets while remote sensing satellite observations provide cost effective alternatives with better spatial extent and temporal frequency. Remote sensing is one of the effective technologies to map the areal extent of the crops using optical as well as microwave/Synthetic Aperture RADAR (SAR) sensors. Cloud cover is the major problem faced in using the optical datasets during monsoon (June to Sept. locally called Kharif season). Hence, Sentinel-1 C-band (center frequency: 5.405 GHz) RADAR sensor launched by European Space Agency (ESA) which has an Interferometric Wide-swath mode (IW) with dual polarization (VV and VH) has been used for rice area mapping. Limited studies have attempted to establish operational early season rice area mapping to facilitate local governance, agri-input management and crop growers. The key contribution of this work is towards operational near real time and early season rice area mapping using multi-temporal SAR data on GEE platform. The study has been carried out in four districts viz., Guntur, Krishna, East Godavari and West Godavari from Andhra Pradesh (AP), India during the period of Kharif 2017. The study region is also called as coastal AP where rice transplanting during the Kharif season is carried out during mid Jun. till Aug. and harvesting during Oct. to mid Dec. months. The training data for various classes viz, Rice, NonRice-Agriculture, Waterbodies, Settlements, Forest and Aquaculture have been obtained from GEE, Global Land Cover (GLC) layers developed by ESA and field observations. We have evaluated the performance of Random Forest (RF) classifier by varying the number of trees and incrementally adding the SAR images for model training. Initially the model has been trained considering two images available from mid June 2017. Further, various models have been trained by adding one consecutive image till end of August 2017 and classification performance has been evaluated on validation dataset. The classified output has been further masked with agriculture non-agriculture layer derived from global land-cover layer obtained from ESA. Analysis shows that incremental addition of temporal observations improves the performance of the classifier. The overall classification accuracy ranges between 78.11 to 87.00%. We have found that RF classifier with 30 trees trained on six images available from mid June till end August performed better with classification accuracy of 87.00%. However, accuracy assessment performed using independent stratified random sampling approach showed the classification accuracy of 84.45%. An attempt is being made to follow the proposed approach for current (i.e. 2018) season and provide incremental rice area estimates in near real-time.

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences

In season crop area mapping is of significant importance for multiple reasons such as monitoring ... more In season crop area mapping is of significant importance for multiple reasons such as monitoring if crop health and residue burning areas, etc. Wheat is one of the important cereal crop cultivated all across the India, with Punjab-Haryana being the prime contributors to the total production. In this study we propose a method for early season Wheat area mapping using the combined use of temporal Sentinel-1 and 2 observations. Further, we propose a method to estimate the crop phenology parameter viz. sowing date using the early time series of Normalized Difference Vegetation Index (NDVI). Few districts from Haryana and Punjab have been selected. The Wheat sowing starts in month of Oct.-Nov. Considering the sowing window, images available during Oct.-Dec. 2017 have been chosen for early season Wheat area mapping. The field data for Wheat, other crops, forest, water and settlements classes is gathered using human participatory sensing and Google Earth Engine (GEE) platform and used for data analysis. We have assessed the performance of random forest classifier using 1. NDVI derived from Sentinel-2, 2. VV and VH backscatter obtained from Sentinel-1 and 3. Both NDVI and VV-VH backscatter. Results show the maximum classification accuracy of 88.31 % when using combination of NDVI, VV and VH. However, accuracy drops to 87.19 % and 79.16 % while using NDVI and VV-VH respectively. Further, to estimate the sowing date we have considered the NDVI time-series during Oct.-Dec. for Wheat pixels. A method based on NDVI compositing is used with gradual increase of 0.1-0.15 at every 12 days for subsequent two images. We have found a good agreement between the estimated sowing dates and actual sowing dates.

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences

Satellite based earth observation (EO) platforms have proved capability to spatio-temporally moni... more Satellite based earth observation (EO) platforms have proved capability to spatio-temporally monitor changes on the earth's surface. Long term satellite missions have provided huge repository of optical remote sensing datasets, and United States Geological Survey (USGS) Landsat program is one of the oldest sources of optical EO datasets. This historical and near real time EO archive is a rich source of information to understand the seasonal changes in the horticultural crops. Citrus (Mandarin / Nagpur Orange) is one of the major horticultural crops cultivated in central India. Erratic behaviour of rainfall and dependency on groundwater for irrigation has wide impact on the citrus crop yield. Also, wide variations are reported in temperature and relative humidity causing early fruit onset and increase in crop water requirement. Therefore, there is need to study the crop growth stages and crop evapotranspiration at spatio-temporal scale for managing the scarce resources. In this s...