Environmental Data Analysis and Mining

The main objective of this course is to provide an overview of the concepts, techniques, methodologies and types of tools that allow the analysis and management of data with a geospatial and environmental nature, to support decision-making. This objective is broken down into two large parts. On the one hand, an overview of the main paradigms related to data storage and management will be provided, focusing interest on the field of environmental data. In this part, data management and querying environments will be shown, both of a more traditional (relational) nature and from the field of Big Data. The second part will focus on the use of knowledge extraction methods (data mining) from data sources that may present spatial and temporal dimensions, typical of environmental data. More specifically, and in line with what has already been indicated in the degree description official document, the expected learning results of this course can be summarized as follows.

- Know the fundamentals of the modeling and storage of environmental data.
- Learn about Big Data platforms and technologies.
- Be able to use data management, querying, analysis and visualization tools.
- Know and apply the main data clustering techniques.
- Know and apply the main techniques of intelligent data classification and regression.

The contents that are developed in the course are articulated around those indicated in the course descriptors included in the official document of this master’s degree.

- Modeling and data storage.
- Management and querying of data.
- Exploratory analysis and visualization.
- Clustering methods.
- Intelligent classification and regression methods.

The course syllabus is divided into 5 chapters, corresponding to the 5 content elements above. These topics will be covered through a short theoretical introduction and a more extensive practical approach.

Basic Bibliography

A. Silberschatz, H.F. Korth, S. Sudarshan, Database System Concepts, 6th Edition, McGraw-Hill, 2014.

Oded Maimon, Lior Rokach, Data Mining and Knowledge Discovery Handbook, second edition, Springer, 2010

Yanchang Zhao, R and Data Mining, first edition, Springer, 2012. Online version available at: http://www.rdatamining.com


Further reading
Roger S. Bivand, Edzer J. Pebesma, Virgilio Gómez-Rubio, Applied Spatial Data Analysis with R, Springer, 2008.

Shashi Shekhar, Sanjay Chawla, Spatial Databases: A tour, Prentice Hall, 2003

Sadalage, Fowler. NoSQL Distilled: A Brief Guide to the Emerging World of Polyglot Persistence, Addison-Wesley, 2012

Marz, N., Warren, J. Big Data: Principles and best practices of scalable realtime data systems, Manning Publications, 2015.

In this course, the student will acquire or practice a series of generic competences, desirable in any university degree, and specific competencies of either engineering or environmental engineering.

In accordance with the table of competences that was designed for the degree, the work in the course will be done towards the acquisition of the following competences.

Basic competences

CB 6. Possess and understand knowledge that provides a basis or opportunity to be original in the development and/or application of ideas, often in a research context.
CB 7. That students know how to apply the acquired knowledge and their ability to solve problems in new or not well-known environments within broader (or multidisciplinary) contexts related to their area of study.
CB 8. That students can integrate knowledge and face the complexity of formulating judgments based on information that, being incomplete or limited, includes reflections on the social and ethical responsibilities linked to the application of their knowledge and judgments.
CB 9. That students know how to communicate their conclusions and the ultimate knowledge and reasons that support them to specialized and non-specialized audiences in a clear and unambiguous way.
CB 10. That students have the learning abilities that allow them to continue studying in a way that will have to be largely self-directed or autonomous.

General Competences

GC 2. Being able to predict and control the evolution of complex situations through the development of innovative work methodologies adapted to the specific scientific/research, technological or professional field, generally multidisciplinary, in which their activity is carried out.
GC 3. Being able to take responsibility for their own professional development and their specialization in one or more fields of study.
CG 5. Carry out the appropriate research, undertake the design and direct the development of engineering solutions, in new or little-known environments, relating creativity, originality, innovation and technology transfer.

Transversal Competences

TC 3. Adapt to changes, being able to apply new and advanced technologies and other relevant developments, with initiative and an entrepreneurial spirit.
CT 4. Demonstrate critical and self-critical reasoning, analytical and synthesis capacity.
TC 6. Appreciate the value of quality and continuous improvement, acting with rigor, responsibility and professional ethics within the framework of commitment to sustainable development.

Specific Competences

CE 2. Know in depth the technologies, tools and techniques in the field of environmental engineering to be able to compare and select technical alternatives and emerging technologies
CE 3. Develop sufficient autonomy to participate in research projects and scientific or technological collaborations within the thematic field of Environmental Engineering, in interdisciplinary contexts and, where appropriate, with a high component of knowledge transfer.
CE 5. Conceptualize engineering models, apply innovative methods in solving problems and adequate computer applications for the design, simulation, optimization and control of processes and systems.
CE 9. Possess the autonomous learning skills to maintain and improve the skills of Environmental Engineering that allow the continuous development of the profession.

The teaching methodology used in this course will combine the use of master classes, in which general concepts will be introduced, with practical lessons in the lab, through which students will be introduced to a representative subset of related technologies, and with a group work in which the students will apply these technologies to a specific use case. These activities will be complemented with individual and group assistance sessions. The course can be followed both in person and through telematic teaching tools. Specifically, in this matter, the USC virtual teaching facilities will be used as asynchronous communication tools with the students to distribute all the material related to daily work in the classroom, to share information related to the evaluation and to collect works delivered by the student body. Microsoft TEAMS will also be used as a synchronous communication and online teaching tool.

The material shared with the students will consist of:
- The teaching guide of the subject
- Weekly planning of the activities carried out in the classroom and work delivery schedule.
- Presentations and videos related to the theoretical part of the course.
- Videos related to the practical sessions.
- Practical work guides for the lab sessions and description of the related work to deliver.
- Description of the group work to be carried out.

The teaching activities that will be carried out in this area are listed below:

Theory classes (4 hours in the room): In these classes, work will be done related to the main concepts of the 5 topics into which the course content is organized. In order get profit from these sessions, it will be important for students to review the material provided beforehand, which includes slides and videos.

Laboratory practices (18 hours in the room): In these sessions there will be tutorials on the use of some representative technologies. In addition to accompanying the student in the process of experimentation with technology, small problems will be raised to be solved through its use.

Group work (autonomous work): In this activity, students organized into small work teams will use data technologies to address a decision-making problem in the field of environmental engineering.

Evaluation of the group work (2 hours in the room): The students will present the results of the group work in a public session.

Final exam (2 hours in the exam room): This exam will evaluate the acquisition of the general knowledge explained in the theoretical sessions and also the skills in the use of the main concepts related to the representative tools with which they worked in the practical sessions.

In cases of fraudulent completion of exercises or tests, the provisions of the Regulations for evaluating student academic performance and grade review will apply.

Overall, the evaluation of this course will be carried out through a continuous evaluation with a total weight of 70% and a final test with a weight of 30%.

Activities included in the Continuous Evaluation (70% of the evaluation)

- Carrying out practical work (30% of the evaluation): The students will individually solve problems related to environmental data using the technologies seen in the laboratory practical classes.
- Teamwork (40% of the evaluation): Students organized in small groups will solve a problem related to decision-making in the field of environmental engineering. The ambition of the proposed objectives, the quality of the proposed solution, the quality of the documentation delivered and the presentation of the results in the public session will be valued.

Final exam (30% of the evaluation)

- The exam will be divided into two parts. A first part in which the students will have to develop in a limited space an explanation of the requested concepts. The assessment will be based on both the completeness of the response (taking into account the space provided to develop it) and its precision and correctness. In the second part, students will have to answer specific questions related to laboratory works.

The student will be considered as "not presented" if he/she does not attend any evaluation activity (exam, laboratory or group assignments).

Those who have to attend the second opportunity will keep the qualifications obtained in the continuous evaluation, that is, the qualifications of the laboratory practices and teamwork. In case of not having passed the continuous evaluation, it will be necessary to carry out additional work related to it.

The evaluation of the competences is foreseen as follows:
- Laboratory practices: CB7, CB10, CG2, CG5, CE2, CE3, CE5
- Group work: CB7, CB8, CB9, CB10, CG2, CG3; CG5, CT3, CT4, CT6, CE3, CE5, CE9
- Final exam: CB6, CB9, CT4, CT6, CE2, CE3, CE5

The student's autonomous work outside the classroom will be divided into three main parts: i) Review of the materials presented in the lectures and exam preparation. ii) Individual resolution of the problems proposed in the context of laboratory practices. iii) Conceptualization, design and implementation of necessary solutions for group work. The student will also need hours to prepare documentation and prepare the public defense of the group work.

In order to achieve the proposed objectives in this course, it is recommended to maintain a very fluid communication with the teaching staff, in order to solve all the problems that may arise related to competences in the field of data management.

It will be necessary to have a computer in which the necessary software components can be installed to follow the laboratory practices and to carry out the group work. It is important to go to the assistance sessions to be able to resolve all incidents related to the installation and use of this software as quickly as possible.

Access to the USC virtual teaching facilities and the Microsoft TEAMS online teaching environment will be necessary, the latter in case of following the classes online.

The teaching language of the course will be Spanish in line with the strategic decision of the Master, which defined the recruitment of students from other autonomous communities or countries as essential. In case of having difficulties with Spanish, the teaching staff may provide some type of assistance through additional material in English.