The Combination between Machine Learning and Sustainable Development Goal (SDG)

By: Dr. Sunil K Singh , Shabeg Singh Gill

Machine learning is a division of artificial intelligence that studies how systems can learn from data. It studies computer algorithms which in turn help in identifying patterns in data and making significant decisions. Data is fed as input to machine learning algorithms and then various statistical formulas are employed to get the most desired and accurate results.

It is expected that there will be 10 billion people in urban cities by 2030 worldwide. To achieve the quickly increasing world population, globalization, hyper-urbanization, economy, environmental stability, the effective and efficient use of all global resources by every country becomes an important essential part. In the present stage, around 55% of the worldwide population resides in urban cities, and this is expected to rise to 70% by 2050 and increasing 2.5 billion in the next three decades.  For this, environmental, social, and economical sustainability is a must to keep pace with the rapid expansion of people and the nature which must be an integral step toward stability of the world. These requirements are not specified by any individual but agreed by every one of the 193 countries at the United Nations and have been put as one of the Sustainable Development Goals (SDGs) in 2015 [1]. The SDGs provides a shared blueprint for peace and prosperity for people and the planet as 2030 Agenda for Sustainable Development. There are 17 Sustainable Development Goals (SDGs) and 169 targets  are identified which are adopted and take as an vital call for action by all countries both developed and developing nations , in a global corporation. The key objective of SGDs to end the poverty and other deprivations, must move along with policies that improve health, education, reduce inequality, protect environment, economic growth, smart cities  – all while undertaking climate revolution and working to reserve our oceans and forests.

AI could assistance to  accomplish around 80% of the Sustainable Development Goals (SDGs). AI could become a key tool for enabling a rotary economy and building smart cities that use their resources effectively and efficiently. Machine leaning is an subset of Artificial Intelligence (AI) that help to understands the  sustainable development needs to design, execute, advise and to plan the future of our planet and its sustainability in more effectively, among many other matters[2].

Figure 1:  The list of 17 Sustainable Development Goals (SDGs) announce by UN in 2015[1]

Sustainability implies utilizing natural resources efficiently and saving for future generations in order to maintain ecological balance. Sustainable engineering is the way by which we can build a product using limited resources. Machine learning plays a vital role in the development of sustainable technology. It can help to predict a residential area’s energy efficiency by employing classifiers such as decision trees. Similarly, a framework can be developed for sustainable hydropower generation in reservoirs by using supervised learning – Bayesian Linear Regression, Neural Networks, and Decision Trees. Commercial building energy consumption can be estimated using SVM and Random Forest. A model can be developed for the optimization of environmental protection for goods as well as industrial facilities through Neural Networks and Bayesian Network Models. Priorities of sustainable development can be comprehended through machine learning( KNN, Naive Bayes, Decision Trees, SVM). Accurate weather files can be generated through hybrid machine learning models. The sustainability of projects can be enhanced through NLP applications[3]. The yield of food crops can be estimated by employing Deep Learning and Reinforcement Learning models. Machine learning ensemble methods, namely, Decision Trees, K nearest neighbors, and Support Vector Machines are useful in wind power prediction.  Machine learning play a significant role to offer intelligent computational environment like as reconfigurable computing [4], ubiquitous computing [5], and other. In the recent time, many technological tools has been developed to provide fast and effective information health information (SDG-3) during COVID-19 Pandemic, that offer greater help to people health [6]. 

Supervised and unsupervised machine learning techniques are being used highly to improve efficiency in numerous fields (Telecom, Agriculture, Operations), as a result, moving towards sustainable development. Specific machine learning algorithms are used in specific areas to promote sustainable engineering. It is worth mentioning here that there a lot research is going in transmission and communication area where how ML can monitor and manage the network bandwidth to provide fast communication in real time network load [7]. In most of the examples discussed above, the prime approach is to use fewer safe and affordable resources and in turn, save for future generations.

In the future, it would be possible to deploy machine learning models in many SDG targets and indicators and as a result, the integration of machine learning with a sustainability approach, will provide us with the most desirable results and in turn provide for a greener future. It is also suggested that innovative policies are essential to confirm that the effect of new technologies is playing a vital role in the efficiency, ethics, and sustainability of global goals prior to initiation and deploying ML concept. If everyone is looking for a future of peace, self-respect and opportunity, then technology and innovation need to be taken as central part to achieve the 17 Sustainable Development Goals by 2030 in true and transparent manner.

References

  1. Sustainable Development Goals and targets descriptions can be accessed at United Nation
  2. Vinuesa, R., Azizpour, H., Leite, I. et al. The role of artificial intelligence in achieving the Sustainable Development Goals. Nat Commun 11, 233 (2020).
  3. Chopra, M., Singh, S. K., Aggarwal, K., & Gupta, A. (2022). Predicting Catastrophic Events Using Machine Learning Models for Natural Language Processing. In Data Mining Approaches for Big Data and Sentiment Analysis in Social Media (pp. 223-243). IGI Global.
  4. Singh, S. K., Singh, R. K., & BHATIA, M. S. (2010). System level architectural synthesis & compilation technique in reconfigurable computing system. In ESA 2010: proceedings of the 2010 international conference on embedded systems & applications (Las Vegas NV, July 12-15, 2010) (pp. 109-115).
  5. Singh, S. K., Kaur, K., & Aggrawal, A. (2014). Emerging Trends and Limitations in Technology and System of Ubiquitous Computing. International Journal of Advanced Research in Computer Science, 5(7).
  6. Aggarwal, K., Singh, S. K., Chopra, M., & Kumar, S. (2022). Role of Social Media in the COVID-19 Pandemic: A Literature Review. Data Mining Approaches for Big Data and Sentiment Analysis in Social Media, 91-115.
  7. Gupta, S., Singh, S. K., & Jain, R. (2010). Analysis and optimization of various transmission issues in video streaming over Bluetooth. International Journal of Computer Applications, 11(7), 44-48.

Cite this article as:

Dr. Sunil K Singh, Shabeg Singh Gill (2022), The Combination between Machine Learning and Sustainable Development Goal (SDG), Insights2Techinfo, pp.1

44090cookie-checkThe Combination between Machine Learning and Sustainable Development Goal (SDG)
Share this:

Leave a Reply

Your email address will not be published.