Satellite big data analytics for decision intelligence - A multi-case study approach

Abstract

The four essays of this dissertation contribute to the use of satellite big data analytics for decision intelligence. Utilizing established methodological foundations in case studies, we study scenarios in various sectors such as energy, humanitarian disaster relief operations, and agriculture where satellite big data analytics can provide decision intelligence. We specifically look at some of the real-life settings in these sectors in India and assess how satellite big data analytics can provide to answer select research questions. The research results support decision-makers in coping with Volatility, Uncertainty, Complexity, and Ambiguity (VUCA) supply chain environments. The first research paper, “Open Innovation using Satellite Imagery for Initial Site Assessment of Solar Photovoltaic Projects”, studies the adoption of solar energy in countries like India which is propagating mainly through the development of energy producing photovoltaic farms. The realization of solar energy producing sites involves complex decisions and processes in the selection of sites whose knowhow may not rest with all the stakeholders supporting (e.g. banks financing the project) the industry value chain. In this paper, we use the region of Bangalore in India as the case study to present how open innovation using satellite imagery can provide the necessary granularity to specifically aid in an independent initial assessment of the solar photovoltaic sites. We utilize the established analytical hierarchy process over the information extracted from open satellite data to calculate an overall site suitability index. The index takes into account the topographical, climatic and environmental factors. Our results explain how the intervention of satellite imagery based big data analytics can help in buying the confidence of investors in the solar industry value chain. Our study also demonstrates that open innovation using satellites can act as a platform for social product development. The second essay, “Management of Humanitarian Relief Operations using Satellite Big Data Analytics: The Case of Kerala Floods”, discusses how disasters lead to breakdown of established Information and Communication Technology (ICT) infrastructure. ICT breakdown obstructs the channel to gather real-time last mile information directly from the disaster-stricken communities and thereby hampers the agility of humanitarian supply chains. This creates a complex, chaotic, uncertain, and restrictive environment for humanitarian relief operations, which struggles for credible information to prioritize and deliver effective relief services. In this paper, we discuss how satellite big data analytics built over real-time weather information, geospatial data and deployed over a cloud-computing platform aided in achieving improved coordination and collaboration between rescue teams for humanitarian relief efforts in the case of 2018 Kerala floods. The analytics platform made available to the stakeholders involved in the rescue operations led to timely logistical planning and execution of rescue missions. The developed platform improved the accuracy of information between the distressed community and the stakeholders involved and thereby increased the agility of humanitarian logistics and relief supply chains. This research proves the utility of fusing data sources that are normally sitting as islands of information using big data analytics to prioritize humanitarian relief operations. The third essay, Satellite Big Data Analytics for Ethical Decision Making in Farmer’s Insurance Claim Settlement – Minimization of Type-1 & Type-II errors, investigates the crop failure claims to insurance providers when affected by sowing/planting risk, standing crop risk, post-harvest risk, and localized calamities risk. Decision making for settlement of claims submitted by farmers has been observed to comprise of type-1 and type-II errors. The existence of these errors reduces confidence on agri-insurance providers and government in general as it fails to serve the needy farmers (type-I error) and sometimes serve the ineligible farmers (type-II error). The gaps in currently used underlying data, methods and timelines including anomalies in locational data used in crop sampling, inclusion of invalid data points in computation, estimation of crop yield, and determination of the total sown area create barriers in executing the indemnity payments for small and marginal farmers in India. In this paper, we present a satellite big data analytics based case study in a region in India and explain how the anomalies in the legacy processes were addressed to minimize type-I and type-II errors and thereby make ethical decisions while approving farmer claims. Our study demonstrates what big data analytics can offer to increase the ethicality of the decisions and the confidence at which the decision is made, especially when the beneficiaries of the decision are poor and powerless. The fourth essay, Digitalisation of decision making using satellite big data analytics: a case study from India’s agri-insurance sector, explores how digitalisation based on satellite big data analytics can help India’s agriculture sector. The sector suffers from uncertainty in performance of farms due to weather fluctuations and other risks is tackled by providing insurance cover. However, policymaker’s choice of administrative measures for estimating crop loss has resulted in inaccurate data collection, opened vulnerability to politicization of the process and created bottlenecks to operate at scale. These problems have led to skewed timelines for data collation, lack of confidence of the data produced by the agri-insurance providers and caused long drawn delays in settling claims made by farmers. In this paper, we present a case study on how digitalization using satellite big data analytics deployed in the Northern Indian district of Bhiwani has attempted to solve the aforementioned problems between the stakeholders in the agri-insurance claim settlement process. This essay is an extension to the third essay and puts into limelight how satellite big data based analytics provides an independent data source and digitalization assisted decision-making platform for the agri-insurers to conduct an unbiased assessment into the total acreage of the crop as well as the total yield of the crop which are the two main parameters for calculating the indemnity payments. The third essay looks at the effect on farmers and that motivated us to look at the root causes. This essay explores the root causes from the perspective of reviewing the data collection, dissemination in agri-insurance operations. The results showcase how transparency brought in by digitalization using satellite big data analytics curbs the plausible exploitation of claim settlement process and leads to provisioning increased efficiency and efficacy in settling claims for small and marginal farmers. Show more