DATA DRIVEN MODELING FOR ENGINEERS

Big data and the algorithms used in data science, together with the corresponding process and its technology tools, have important implications for addressing climate change. From machine learning algorithms to data visualization, data science methods are used to investigate and better understand climate change and its various effects on land, sea, food, etc.Data science is a powerful approach which is capable of helping practitioners, and policy-makers understand the uncertainties and ambiguities inherent in data, to identify interventions, strategies, and solutions that realize the benefits for humanity and the environment, and to evaluate the multiple– and sometimes conflicting–goals of decision-makers. In this MOOC course, we introduce methods pertaining to the growing field of data science and apply them to issues relevant to climate change. Topics Data science Analytics as a process Data-driven decisions Climate change Applications of data science in climate change Course content Understand data science Learn about the sources of big data Understand the basics of climate change, its impacts and sustainable development goals Get to know data-driven decisions and how they are made Highlight some climate change challenges that are directly or indirectly related to data science Apply data science knowledge and skills to make climate change related decisions Learn how others have used data science in association with addressing climate change problems You will learnBy the end of the course, you will be able to: obtain and analyze datasets; make data-driven decisions; identify and address climate change challenges using data science Who is the course for?This course is designed for those who want to improve their analytics and data-driven decision-making skills, with an emphasis on utilizing such skills for addressing climate change challenges. The course will also be useful for practitioners and policy-makers as they can benefit from understanding the uncertainties and ambiguities inherent in data and using it to identify interventions, strategies, and solutions that realize benefits for humanity and the environment.

The information and communication technology (ICT) sector is responsible for approx. 1.8-2.8% of the global greenhouse gas (GHG) emissions in 2020, and software is both part of the problems and the solutions. Traditional software engineering principles and techniques do not consider the climate, environment, and sustainability aspects in building and using software for any purpose. We, software engineers, developers, researchers, climate scientists, and various other related stakeholders, need to think about how we can reduce the carbon footprint due to building and using software-intensive systems. Green and sustainable software engineering is an emerging concept that can help reduce the carbon footprint related to software. In this introductory course, we will introduce the concept of green and sustainable software engineering and the engineering process to build green and sustainable software. Topics Sustainable and green computing Sustainable and green software engineering Process Energy efficient computing Sustainability issues in Scientific computing You will learnBy the end of the course, you will be able to: analyze the green and sustainability issues in traditional software engineering, identify and incorporate key elements to be included in the software engineering process to make the software green and sustainable, and use techniques to make your software code energy efficient. Who is the course for?This course is designed for those who are software developers, managers and software related policy makers, or have knowledge about software development, and want to consider the green and sustainability aspects in their everyday life. Also, this course will be useful for computational scientists who build green software and want to know more about these aspects in software engineering. However, this is an introductory course, and it will show a path for life-long learning to build more in-depth knowledge in each concept introduced in this course.

Undervisningen ges på svenska. Viss undervisning på engelska kan förekomma. Att etablera en datadriven kultur i en grupp eller i ett team är inte lätt. En datadriven kultur innebär att gruppens medlemmar ofta använder olika typer av verktyg för att analysera data och diskuterar sina insikter, innan de fattar beslut. I den här kursen får du lära dig hur mognadsgraden av datadriven kultur kan etableras och mätas i en befintlig grupp. Lär dig förstå vad datadriven kultur är och hur mognadsgraden kan analyserasKursen består av två delar: en mognadsanalys och en åtgärdsplan.  Först kommer du att få genomföra en mognadsanalys av datadriven kultur i en befintlig grupp i din egen verksamhet. Mognadsanalysen är baserad på tidigare forskning inom Analytics och grupputveckling (ex Wheelans modell).  Utifrån genomförd mognadsanalys kommer du att få ta fram en åtgärdsplan som är förankrad i aktuell forskningslitteratur.  Vem är kursen för? Kursen riktar sig till dig som är yrkesverksam och intresserad av att lära dig mer om hur en datadriven kultur kan etableras och analyseras i en grupp eller ett team.  Efter avslutad kurs kan du: genomföra en mognadsanalys av datadriven kultur i en grupp, och ta fram en åtgärdsplan som är förankrad i aktuell forskningslitteratur för hur en grupp skapar förutsättningar för en ökad mognadsgrad.  Kursformat Kursen är i sin utbildningsform och omfattning tänkt att kombineras med arbete. Det innebär bland annat att: Kursen ges online och genomförs genom självstudier samt enstaka frivilliga schemalagda tillfällen där du får möjlighet att träffa övriga kursdeltagare och kursens lärare. (Dessa träffar sker på distans via Zoom) Det är en kort kurs (3 Högskolepoäng) med en studietakt på 10 %. Undervisningen bedrivs främst på svenska, moment på engelska kan förekomma.  Behörighet Om du inte uppfyller de formella behörighetskraven kan du få din behörighet bedömd på reell kompetens, kunskap och kompetens som du har fått på annat sätt, såsom arbetslivserfarenhet, övriga studier med mera. Läs mer under his.se/sokwiser.  Utvecklad inom WISER Kursen är utvecklad inom projektet WISER. Vi erbjuder skräddarsydda kurser för digital transformation och riktar sig till dig som är yrkesverksam. Projektet samfinansieras av KK-stiftelsen inom ramen för Expertkompetens. För mer information besök: his.se/wiser.    

This course explores the role of intelligent sensor systems in driving sustainability and enabling the green transition. Participants will learn the fundamentals of sensor technologies and their integration into intelligent, distributed systems. Emphasis is placed on applications in energy efficiency, environmental monitoring, and sustainable automation. The course covers topics such as basic sensor technologies, embedded systems, distributed computing, low-resource machine learning approaches, and federated learning for privacy-preserving, decentralized model training across sensor nodes. Through a combination of lectures, practical examples, and hands-on project work, participants will gain experience in designing and deploying intelligent sensor systems tailored to real-world sustainability challenges. The students bring their own case study example as the background for a practical project, through which the student is also finally examined. Recommended prerequisites: At least 180 credits including 15 credits programming as well as qualifications corresponding to the course "English 5"/"English A" from the Swedish Upper Secondary School. Online meetings (estimated): 14 Oct.: Introduction11 Nov.: Project Idea16 Dec.: Project Presentation Study hours: 80 This course is given by Örebro University.

Understanding and optimizing battery performance is crucial for advancing electrification, sustainable mobility, and renewable energy systems. This course provides a comprehensive overview of battery performance, ageing processes, and modelling techniques to improve efficiency, reliability, and service life. Participants will explore battery operation from a whole-system perspective, including its integration in electric vehicles (EVs), charging infrastructure, and energy grids. The course covers both physics-based and data-driven modelling approaches at the cell, module, and pack levels, equipping learners with tools to monitor, predict, and optimize battery performance in real-world applications. Through this course, you will gain the ability to assess battery health, model degradation, and evaluate second-life applications from both technical and economic standpoints. Course content Battery fundamentals and degradation mechanisms Battery modelling Battery monitoring and diagnostics Operational strategies for battery systems Techno-economic performance assessment Battery second-life applications   You will learn to: Explain the principles of battery operation and degradation mechanisms. Develop battery performance models using both physics-based and data-driven approaches. Apply methods for State of Health (SOH) estimation and Remaining Useful Life (RUL) prediction. Analyze key factors influencing battery lifespan economics in different applications. Evaluate battery second-life potential and identify suitable applications. Target group: Professionals in energy, automotive, R&D, or sustainability roles Engineers and data scientists transitioning into battery technologies Technical specialists working with electrification, battery management systems, or energy storage

Batteries and battery technology are vital for achieving sustainable transportation and climate-neutral goals. As concerns over retired batteries are growing and companies in the battery or electric vehicle ecosystem need appropriate business strategies and framework to work with.This course aims to help participants with a deep understanding of battery circularity within the context of circular business models. You will gain the knowledge and skills necessary to design and implement circular business models and strategies in the battery and electric vehicle industry, considering both individual company specific and ecosystem-wide perspectives. You will also gain the ability to navigate the complexities of transitioning towards circularity and green transition in the industry.The course includes a project work to develop a digitally enabled circular business model based on real-world problems. Course content Battery second life and circularity Barriers and enablers of battery circularity Circular business models Ecosystem management Pathways for circular transformation Design principles for battery circularity Role of advanced digital technologies Learning outcomes After completing the course, you will be able to: Describe the concept of battery circularity and its importance in achieving sustainability goals. Examine and explain the characteristics and differences of different types of circular business models and required collaboration forms in the battery- and electric vehicle- industry. Analyze key factors that are influencing design and implement circular business models based on specific individual company and its ecosystem contexts. Analyze key stakeholders and develop ecosystem management strategies for designing and implementing circular business models. Explain the role of digitalization, design, and policies to design and implement circular business models. Plan and design a digitally enabled circular business model that is suitable for a given battery circularity problem. Examples of professional roles that will benefit from this course are sustainability managers, battery technology engineers, business development managers, circular developers, product developers, environmental engineers, material engineers, supply chain engineers or managers, battery specialists, circular economy specialists, etc. This course is given by Mälardalen university in cooperation with Luleå University of Technology Study effort: 80 hrs