Data & Analytics

Data and analytics are increasingly recognized as fundamental elements in achieving the Sustainable Development Goals (SDGs). These 17 goals, adopted by the United Nations in 2015, aim to address global challenges such as poverty, inequality, climate change, environmental degradation, peace, and justice. Each goal is interconnected, requiring a holistic approach to achieve sustainable development by 2030. Within this framework, SDG 17, "Partnerships for the Goals," is particularly crucial as it highlights the need for high-quality, timely, and reliable data to drive progress across all goals.

The importance of data and analytics in realizing the SDGs cannot be overstated. Accurate and insightful data is necessary for several key aspects: assessing current progress, identifying existing gaps, informing policy-making, and guiding the allocation of resources. For instance, in addressing SDG 1, "No Poverty," data helps in understanding the demographics of poverty, allowing for targeted interventions. Similarly, for SDG 3, "Good Health and Well-being," data analytics play a crucial role in tracking disease outbreaks, understanding health trends, and improving healthcare delivery.

In the education sector, under SDG 4, "Quality Education," data can inform about areas where educational resources are lacking or where dropout rates are high, guiding efforts to enhance education systems. Additionally, for SDG 13, "Climate Action," data is indispensable for understanding climate patterns, predicting future scenarios, and formulating strategies to mitigate and adapt to climate change.

Advancements in data collection and analytics methods have opened up new possibilities. Mobile technology, for example, has revolutionized data collection, enabling real-time gathering and dissemination of information even in remote areas. Remote sensing technologies, such as satellite imagery, provide critical data on environmental changes, agricultural patterns, and urban development. These methods not only expand the scope of data collection but also enhance its accuracy and timeliness.

However, challenges remain in harnessing the full potential of data for the SDGs. These include issues related to data availability, quality, accessibility, and interoperability. In many parts of the world, especially in developing countries, there is a significant data deficit. This gap hinders the ability to make informed decisions and effectively address the SDGs. Moreover, data collected must be reliable and relevant to be useful in policy formulation and implementation.

To overcome these challenges, partnerships between governments, private sector, academia, and civil society are vital. These collaborations can foster innovation in data collection and analytics, ensure data sharing, and build capacities for data analysis. Furthermore, there is a need for a global framework to standardize data collection and reporting methods, which will facilitate comparison and aggregation of data across regions and countries.

This paper synthesized current knowledge of mesoscale eddies and their impacts on the marine ecosystem across the North Pacific and its marginal Seas, across the CCS region , the northeastern North Pacific and the Bering Sea, the western boundary of the North Pacific and marginal seas, and the extratropical open North Pacific. How climate change will modify mesoscale processes remains a key open challenge.
This study fills different methodological gaps in the research on the automated detection of stress in office environments
A roadmap for health care leaders to execute intrinsic agency toward equity, supporting SDGs 3 and 10.
Digital health programs are urgently needed to accelerate the adoption of Artificial Intelligence and Clinical Decision Support Systems (AI-CDSS) in clinical settings. However, such programs are still lacking for undergraduate medical students, and new approaches are required to prepare them for the arrival of new and unknown technologies.
In the context of applying machine learning to solve problems for risk prediction, disease detection, and treatment evaluation, EHR pose many challenges– they do not have a consistent, standardized format across institutions particularly in US, can contain human errors and introduce collection biases. In addition, some institutions or geographic regions do not have access to the technology or financial resources necessary to implement EHR, thus resulting in vulnerable and disadvantaged communities not being electronically visible.
This paper show the mathematical and theoretical background of the machine learning algorithm used in this work, the LSTM. The data used are described and the methodology of framework is presented. It shows the predictions results based on LSTM and comparisons with ERA5 and buoy observations.
This paper based on three implemented Regional Climate Models (RCMs), namely CMCC-CCLM, CNRM-ALADIN52, and GUF-CCLM-NEMO, for RCP4.5 and RCP8.5 scenarios of the 21st century. Atmospheric modelling datasets cover the Reference (1971–2000) and Future (2071–2100) Periods of climate projections. The results produced within this study can be used for investigations in specific locations of the Mediterranean basin within integrated hydrologic/hydrodynamic modelling under projected climate change conditions during the 21st century.
The Internet of Things (IoT) has revolutionized the traditional healthcare systems into intelligent system by allowing remote access and continuous monitoring of patient data. Specifically, first a novel scalable blockchain architecture is proposed to ensure data integrity and secure data transmission by leveraging Zero Knowledge Proof (ZKP) mechanism. Then, BDSDT integrates with the off-chain storage InterPlanetary File System (IPFS) to address difficulties with data storage costs and with an Ethereum smart contract to address data security issues.
Evaluating the bias and fairness of ML models has drawn much attention in the machine learning and statistics community. Researchers have proposed methods to assess and mitigate the bias for various applications that could adversely affect underrepresented groups, like recidivism prediction, credit risk prediction, and income prediction.
Our research explores how Stakeholder Capitalism can contribute to global governance to achieve all the 17 SDGs. The main findings revealed that Stakeholder Capitalism and its principles are favorable to foster a friendly environment for achieving most of the SDGs and can contribute to global governance in achieving mainly the SDGs 8, 9, and 17. However, Stakeholder Capitalism literature is incipient for the SDGs 6, 14, and 15, needing further research development by considering non-human stakeholders and the environment.

Pages