Book of Extended summaries ISDA

International Conference on Reimagining Rainfed Agro-ecosystems: Challenges &
Opportunities during 22-24, December 2022 at ICAR-CRIDA, Hyderabad
phone‐enabled information delivery mechanism can help to meet the information needs of
small farmers by reducing their knowledge gaps. Therefore, a mobile app for Unreaped Yield
Potentials of Major Rainfed Crops and Scope for Bridging Yield Gaps ‘was developed based
on developed DSS. It is very useful for the policy makers, researchers, extension workers.
Methodology
It is an android-based app. The database of the app has been designed using SQlite. User
Interfaces were designed. Integrated all the menus and database. This App has been tested with
different datasets and evaluated for its user-friendly environment. The App accommodated 17
rainfed crops viz., rice, sorghum, pearlmillet, maize, fingermillet, chickpea, pigeonpea,
blackgram, greengram, lentil, groundnut, soybean, sunflower, sesame, rapeseed & mustard,
castor and cotton. User has to select a crop and a district cultivating the crop.
Results
The App lists the model districts for a given crop and target District and indicates possible crop
management for bridging yield gap. The App identifies 3 model districts having climate, soil,
share of irrigated area under the crop and share of a particular season in area under the crop
similar to the district (target) selected.
The APP provides climate and available water holding capacity (AWHC) of soil of the district,
area under the crop and share of irrigated area and share of a particular season (in case of rice,
sorghum, maize, blackgram and greengram) in area under the crop and yield of the district in
the crop. It further provides yield achieved by model districts. If the target district itself is the
highest yielding district in the cluster, a remark to this effect is generated. If there are only 1 or
2 districts with yield more than that of target district in a cluster, only those districts will be
listed as model districts. The highest yield among the model districts may be regarded potential
yield. To explore other possible causes of yield gap, information on non-crop specific factors
such as small and marginal farmers (% total farmers), annual rainfall (mm), degraded and waste
lands (% geographical area), groundwater availability (ha m/ sq km), livestock population
(ACU/sq km), rural literacy (%), villages having self-help groups (%), net irrigated area (% net
sown area), villages with all-weather roads (%), households with electricity (%), regulated
markets (No. / lakh holdings), drought proneness (% probability in terms of severe drought),
flood proneness (% area) and cyclone proneness (score on 0-10 scale) were provided for target
district and 3 model districts. The output can be downloaded as word file or in Excel sheet
format for further use. The output of mobile app is shown below.
707 | Page Emerging approaches (RS, AI, ML, Drones etc) for crop management &assessment