OAR@ICRISATRICE YIELD ESTIMATION USING REMOTE SENSING AND CROP SIMULATION MODEL IN NALGONDA DISTRICT, TELANGANAGSnigdhaauthorA study on “Rice yield estimation using Remote Sensing and crop simulation model in Nalgonda district, Telangana” was carried out during kharif, 2021. Precise and real-time agricultural yield data at the national, international and regional levels is becoming increasingly crucial for global food security. Crop yield forecasting could be very useful in advanced crop planning, strategy creation, and management. Because of the importance of yield prediction in food security, the present study used the APSIM-ORYZA model and remote sensing to estimate rice yield. The core objective of this study was to develop a method to integrate remotely sensed data and APSIM model for rice yield estimation in Nalgonda district, Telangana. This study includes mapping of rice growing areas and execution of APSIM model, followed by integration of remote sensing and crop simulation model for rice yield prediction and verification using government statistics. Based on stratification, two villages, Telakantigudem from Kangal mandal and Mallaram village from Kattangoor mandal in Nalgonda district were selected and ten fields from each village were chosen for the study to collect the measured LAI values with the help of ceptometer in the fields and the crop management data from the respected farmers. Crop classification was performed on Sentinel-1 and Sentinel-2 time series data using a Random Forest (RF) classifier and ground reference points collected from field surveys in the Google Earth Engine platform. The results demonstrated an overall accuracy of 92% and a kappa coefficient of 0.85, and rice area was validated with the crop coverage report (kharif, 2021) provided by the Department of Agriculture (DOA), Telangana state showed a relative variation of -0.16%. Remote sensing products like VV, VH AND VH/VV from Sentinel-1 and NIR, Red and NDVI from Sentinel-2 were derived using GEE and were calibrated with the measured LAI data collected from farmers’ fields. The result showed that there was a significant relation (R2=0.78) between NDVI and field LAI and hence it was considered for integration with the crop model output. Maps were derived showing spatial variation in crop extent, and leaf area index (LAI), which are crucial in yield assessment. Execution of APSIM-ORYZA model was done using the weather parameters, soil parameters, genetic coefficients and crop management data. The evaluation of the model with simulated yield and observed yield in the farmers’ fields showed linear regression of R2 = 0.79, root mean square error (RMSE)=804 kg ha-1 and mean absolute error (MAE)=728 kg ha-1. The overall spatially averaged model yield for the district showed 4925 kg ha-1 which is deviated by 2% from the average yield in the government statistics with 5024 kg ha-1. The study showed that by assimilation of remotely sensed data with the crop models, crop yields before harvest could be successfully predicted.Remote SensingRice2022Professor Jayashankar Telangana State Agricultural University;Water Technology CentreThesis

For work being deposited by its own author: In self-archiving this collection of files and associated bibliographic metadata, I grant OAR@ICRISAT the right to store them and to make them permanently available publicly for free on-line. I declare that this material is my own intellectual property and I understand that OAR@ICRISAT does not assume any responsibility if there is any breach of copyright in distributing these files or metadata. (All authors are urged to prominently assert their copyright on the title page of their work.)

For work being deposited by someone other than its author: I hereby declare that the collection of files and associated bibliographic metadata that I am archiving at OAR@ICRISAT) is in the public domain. If this is not the case, I accept full responsibility for any breach of copyright that distributing these files or metadata may entail.

Clicking on the deposit button indicates your agreement to these terms.