[month] [year]

Mamatha – Weather-based decision

October 2022

Alugubelly Mamatha received  her  doctorate in Computer Science and Engineering (CSE). Her research work was supervised by Prof. Krishna Reddy. Here’s a summary of her research work Improving Reuse in Weather-based Decision Support Systems:

The weather observation and forecasting systems have become vital to every country for improving the efficiency of several systems that deal with life and property. Over the years, the weather information and forewarning systems are gradually becoming powerful, domainspecific, and location-specific. Weather-based decision support systems (DSSs) are being built to improve the efficiency of healthcare delivery, agricultural production systems, transportation sector, governance systems, and so on. In a weather based DSS, given a weather situation, the domain experts prepare the appropriate suggestions to improve the efficiency of the stakeholders. Once the domain experts prepare a suggestion for a given weather situation, there is a scope to reuse the same suggestion for the similar weather situations in the future. As a result, the performance of the weather based DSS could be improved. Notably, the notion of reuse is widely applied to improve the performance of DSSs in multiple domains. For example, the notion of reuse is widely applied to reduce the software development cost in the software domain. Notably, in the literature, the concept of reuse is not being explored to improve the performance of weather based DSS. In this thesis, we introduced the problem context and proposed two frameworks to improve reuse in weather based DSSs. As a part of the problem context, we defined two notions, viz. weather condition (WC) and coupled WC, to capture two types of weather situations. Moreover, we have defined the notions of cycle, period, temporal reuse, spatial reuse and coverage percentage metric. As the first approach, we proposed a framework to improve reuse by proposing the notion of Category-based WC (CWC). The basic idea is that it is possible to improve the performance of weather-based DSS by exploiting the weather-based categories of the given domain. By considering the weather categories provided by India Meteorological Department (IMD), we have analyzed the extent of temporal reuse among the daily and five-day CWCs by conducting extensive experiments on 30 years of weather data collected at Rajendra Nagar, Hyderabad, Telangana, India. By varying the number of weather variables in CWC from one to five, we have computed the extent of temporal reuse among one-day and five-day CWCs for the following period types: year, season, and phenophases (i.e., growth stages) of the Rice crop. The results show that it is possible to improve reuse significantly with the proposed framework. The results also show that by preparing agro advisories for the first two years, there is a scope to achieve about 80 percent reuse in the third year for all period types. We have also conducted experiments to analyze both temporal reuse and spatial reuse among the CWCs by considering weather data of 12 locations (blocks) in the Telangana state. The results show that it is possible to improve reuse significantly by combining both temporal and spatial reuse. Moreover, we have also conducted validation experiments of the proposed framework by analyzing the similarity among the corresponding real weather-based text advisories during 2016 to 2019. The results show that the proposed framework is exhibiting encouraging results. As the second approach, we presented a framework to improve reuse by proposing the notion of Category-based Coupled WC (CCC). We have analyzed the extent of temporal reuse among the CCC by conducting extensive experiments on 30 years of weather data. The results show that by preparing agro advisories for the first two years, there is a scope to achieve about 60 percent reuse in the third year for all period types. For the agriculture domain, the results provide an opportunity to improve the efficiency of weather-based DSSs by improving the reuse of the weather-based suggestions. The proposed framework is generic and can be applied to any weather based DSS of any given domain. For any domain, the DSS developed under the proposed framework has a potential to reduce the repetition of the work, minimize operational costs and improve the quality of weather-based suggestions.