Course Description

Forest and land fires in Indonesia produce haze that spreads to neighboring countries causing “transboundary haze pollution”. Haze causes decreased visibility that disrupts people as well as causing public health disturbances. Studies on air pollution modelling and haze dispersion have been conducted in order to identify area extent affected by haze.  Data mining as a growing research area has been successfully applied in extracting interesting and important patterns from large datasets. This course gives you the recent development in pollution modeling as well as recent developments on forest and land fire prevention and mitigation efforts in Indonesia.  This course provides an introduction to data mining, basic techniques in data mining, haze and pollutant datasets, and application of data mining techniques in analyzing pollutant datasets.  This course is suitable for students and your lecturers who study or conduct research on computer science, forest and land fires or related fields of study.  On completing this course, students will understand and explain technology developments and data mining methods in pollution modeling as the impact of forest and land fires as well as recent developments on forest and land fire prevention and mitigation efforts in Indonesia.

Learning Outcome
Upon completion of this course, participants will:

1. understand the characteristics of forest and land fires and the associated haze;
2. understand and explain technology developments and methods in pollution modeling as the impact of forest and land fires as well as recent developments on forest and land fire prevention and mitigation efforts in Indonesia.
3. understand and explain basic techniques in data mining that can be applied for smoke haze analysis and pollutants from forest and land fires.
4. be able to use tools to simulate haze dispersion especially from forest and land fire
5. be able to apply basic techniques in data mining on pollutant datasets using R software
6. be able to prepare and present a brief review report on the application of basic techniques in data mining to solve real problems related to forest and land fires.

Teaching Method

1. Course Introduction: 10 hours
2. General Lecture: 12 hours
3. Conceptual Lecture: 12 hours
4. Hands-on Practical: 12 hours
5. Field excursion: 8 hours
6. Independent task: 8 hours
7. Project presentation: 6 hours

Total hours: 68.

Credit Earning System

The total credits earned by participants from this summer course can be transferred to the course: Topics on Applied Data Mining (KOM631), Credit: 3(2-2), which is offered to graduate students of IPB University, especially Master Program in Computer Science or other related courses.