Though the applications of disruptive technologies, i.e., big data, Artificial Intelligence (AI), IoT, cloud computing, and blockchain, were confined to the information technology sector before 21st technology, now these disruptive technologies are part of emerging solutions in almost all of the development sector. For water managers/engineers, policymakers and researchers disruptive technologies are showing promise in many water-related applications such as planning optimum water systems, detecting ecosystem changes through big remote sensing and geographical information system, forecasting/predicting/detecting natural and manmade calamities, scheduling irrigations, mitigating environmental pollution, studying climate change impacts, etc.
This project focuses on developing web-enabled tools and applications to address the data, information, and knowledge gaps in the water sector for strategic water planning and management. These applications and tools will use open data repositories, AI models, and cloud computing platforms to ensure the technology transfer to the Global South without any cost impact.
During the current project period, the use of data and technology in water management will be illustrated through development of three tools /toolkits:
1. Historical flood mapping and prediction of future flood risk using big data and AI
This tool consists of two modules; a flood mapping module that addresses the data gap of historical flood maps and a flood risk predicting module, which addresses the issue of possible risk in the future.
The historical flood mapping module will use a water classification algorithm (Modified Normalized Difference Water Index) applied to ‘stacks’ of historical Landsat and Sentinel 2 satellite imagery to reveal patterns of inundation over space and time across the landscapes. Leveraging the power of Google Earth Engine (cloud computing) resources, on-demand custom requests will deliver products that were not freely available to decision-makers until recently. This tool will enable users to specify the temporal and spatial extent of flooding. It will also allow the user to analyze and control the extent and format of downloadable mapped products. The module will enable more informed decisions on the exposure of people to floods to support preparedness and contingency planning.
The second module will use AI models to predict the future flood risk for a given area. The AI models will be trained using the historical flood maps from the first module, and open temporal datasets including land use land cover, population, infrastructure, precipitation, temperature, and sex and age disaggregated socioeconomic data. This module will help identify the most flood-risky areas for the future. Results will be displayed on the screen and can be downloaded for specified areas at a district or city level.
2. Surface water change detection tool using big data
The surface water change detection tool leverages the extensive archive of Landsat and Sentinel data in the Google Earth Engine archive and Google’s cloud processing power to quickly calculate past patterns of surface water extent from multiple layers of Landsat and Sentinel imagery. The tool will consist of a Google Earth Engine application and a user-friendly web interface that allows the user to specify the period evaluated and other calculation parameters that are then executed in a cloud service. Results will be displayed on the screen and can be downloaded for specified areas.
In the first iteration, the tool will produce a high-quality map of erosion and deposition areas, using the Indus River, Pakistan, after the end of every monsoon season (1984 to 2020) – as a test example. Subsequently, the tool will be customized to provide analytics to other river systems at national or regional levels.
3. Water quality monitoring with IoT sensors
This tool will be designed with a view to assist water quality monitoring in refugee camps in real or near real-time. Currently, water monitoring in refugee camps is done manually and includes: • water quality sampling, • visiting water sources and infrastructure and grading using WHO sanitary scorecard, • visual monitoring of septic tanks,• maintenance of water supply chain,• maintenance of camp water consumption.The toolkit to be developed to replace the above will be a network of interconnected sensors that can transfer data without human interference (i.e.-internet of things – IoT), and a Wi-Fi-based communication medium. Information from sensors will be disseminated among refugees and camp managers through dashboards, which will be hosted on micro-servers.
This near real-time water quality data and information would allow the camp managers to take timely decisions, e.g., a septic tank would be emptied before it overflows and causes spread of disease, a contaminated water source would be identified before the water is consumed by the majority of the refugees, water supply to the camp can be monitored in real-time and water release could be adjusted on an hourly basis, etc.
The same communication channel would be available to the refugees to monitor and report problems related to water infrastructure using a mobile phone application e.g., a broken tap, a leaking or an overflowing septic tank, damaged water pipe, etc.
The project will develop a prototype toolkit, which will be used as a testbed to measure: • the robustness and plug n play ability of the Wi-Fi network• robustness of the sensors being used to monitor various water quality-related parameters• the power consumption of the Wi-Fi network and the sensors• User Interface and User Experience (UI/UX) of the mobile application and web-based dashboard