Continuing from Part 1 which went through how Big Data supports the Sustainable Development Goals (SDGs) 1 to 6 of UN’s 2030 Agenda for Sustainable Development, Part 2 goes through the same for the SDGs 7 to 12.
SDG 7: Affordable and Clean Energy
Thankfully for SDG 7, Big Data Science can help the renewable energy sector through:
- Weather forecast: Predictive analytics and machine learning can be combined with satellite and historical weather data to make weather forecasts, which can then be used to optimise energy production in existing solar, wind and hydro energy plants. For example, IBM’s Hybrid Renewable Energy Forecasting solutions (HyREF) uses cloud-imaging technology and sky-facing cameras to predict the weather in advance. This enables a 10% increase in renewable power generation, which is enough to power 14,000 homes.
- Maintenance management: Maintaining solar plants can be difficult and expensive. A self-storage management company, Extra Storage Space (ESS) uses Big Data to identify when inefficiencies occur without having someone on site. The company’s solar management program, Virtual Irradiance (VI), collects ground level sunlight-intensity data to signal when panels are underperforming and sends an alert that indicates that repairs or maintenance are needed.
SDG 8: Decent Work and Economic Growth
The first thing that came to my colleague’s mind regarding using Big Data to support this SDG is the flexibility of remote goal-driven work. Here’s what he said: “The future is how much work you put in your hours to gain results and not how much hours your put in your work. Work is more and more about learning and generating results, not just to attend somewhere.”
It’s agreeable that it’s a great idea for taking advantage of Big Data Science‘s potential but that’s not what this SDG is referring to. It’s more to do with boosting the economy and creating decent jobs with labour rights protection, as well as expanded access to banking and financial services.
Several studies have shown that economic growth is positively related to job creation. Khan (2007) found that employment elasticity of GDP growth in developing countries is 0.7. Meanwhile, Kapsos (2005) found that for every 1-percentage point of additional GDP growth, total employment grew between 0.3 and 0.38 percentage points during the three periods between 1991 and 2003.
Big Data obtained through mobile phone data can identify shocks in the work force such as large-scale lay-offs, identifying individuals affected by such shocks and predicting changes in aggregate unemployment rates.
SDG 9: Industry, Innovation and Infrastructure
Basic infrastructure like roads, electrical power and access to water and sanitation are still lacking in many developing countries. SDG 9 strives to improve this with access to sustainable infrastructure of high quality, reliability and resilience.
A mixture of satellite and machine learning tech can be used to identify such infrastructure and assess rural communities’ access to them. While working on this article, we learned that there are two ways to use satellite data for infrastructure development:
- University of Alcala researchers Mena and Malpica’s model (2005) for automatic road network extraction is based on satellite and high-res aerial colour imagery. The model uses four components: “data pre-processing; binary segmentation based on three levels of texture statistical evaluation; automatic vectorization by means of skeletal extraction; and finally a module for system evaluation.”
- Jean and the gang’s model (2016) used daytime and nighttime satellite imagery, survey data and machine learning to identify various economic health levels in Malawi, Nigeria, Rwanda, Tanzania and Uganda by referring to features that indicate poverty like roads.
SDG 10: Reduced Inequalities
With income inequality on the rise, it’s more important now than ever that measures are taken to narrow that gap and Big Data can drive these measures, hence SDG 10. We found two examples of data-driven measures:
- China’s targeted poverty aid app: The Chinese government teamed up with China Mobile to develop the Targeted Poverty Alleviation System (TPAS). TPAS is an online platform that gathers data about the poorest areas of China without the need for civil servants to drive all the way to these rural areas for data collection. Villagers are given a special app to update the government with data regarding their villages’ needs, health, food, drinking water conditions, energy, gender equality and education opportunities. This informs the government about what needs to be done to help the villagers. TPAS can also be used to help farmers sell their crops online, like the lotus farmer who managed to sell 20,000 units of lotus in a month thanks to this initiative!
- Automating court processes with AI: Courts can use machine learning to predict an individual’s probability of repeating offenses for court decisions while cutting the bias normally practised by judges. There are two options for addressing a judge’s prejudice against certain groups of people. One is for machine learning to point out to judges when they’ve displayed a history of bias so they can address their biases. The other is to have a machine to recommend sentences based on the details of the case and let the judge approve or appeal.
SDG 11: Sustainable Cities and Communities
The importance of using Big Data to support SDG 11 can’t be emphasised enough. A smart city uses technology to improve aspects of a city’s quality of life through its operations and services.
Reliable sensor data, Internet of Things (IoT) devices, cloud platforms, analytics applications and Machine Learning applications are required to generate relevant real-time insights to enable the development of a smart city.
There are so many aspects of a smart city: energy efficiency, waste management, better housing, better healthcare, smoother traffic flow, air quality control, better water systems, better crime detection, etc.
One example of a smart city initiative is Italy’s major train operator, Trenitalia. Trenitalia installed sensors on the trains to get real-time status updates on each train’s mechanical condition and maintenance predictions for Trenitalia to plan ahead of a breakdown.
This Big Data-driven application of a public transport system can allow a city to prevent major train disruptions and instead provide its train-dependent residents a smooth daily ride to school or work.
SDG 12: Responsible Consumption and Production
In the context of sustainability, less is more. It’s becoming increasingly important that production and consumption of resources like food and energy (connection to SDGs 2 and 7) are sustainable, efficient and not wasteful.
Since SDG 12 is connected to SDGs 2 and 7, the Big Data-driven use cases of those goals in minimising food waste and energy usage can fulfill this goal as well.
SDGs 13 to 17 will be discussed in Part 3, so stay tuned again for the rest of the list. 😉