|
|
課程簡介 Course Introduction
|
|
開課年度學期 Year / Term
|
114 學年度 第 2 學期
|
|
開課班級 Department
|
生態暨環境資源學系碩士班 生態系碩一二合 Master Program, Department of Ecology and Environmental Resources
|
|
授課方式 Instructional Method
|
課堂教學 、 中文
|
|
課程電腦代號 Course Reference Number
|
156006
|
|
課程名稱(中文) Course Title(Chinese)
|
機器學習在環境科學應用
|
|
課程名稱(英文) Course Title(English)
|
Machine Learning in Environmental Sciences
|
|
學分數/時數 Credit Hours
|
3 /
3
|
|
必(選)修 Required / Elective Course
|
選修 Elective
|
|
授課老師 Instructor
|
陳韋妤
|
|
助教 Teaching Assistant
|
|
|
上課時間 Meeting Time
|
星期二,節次8 Tue, Period 8、9、A
|
|
上課教室 Classroom
|
ZB201
|
|
Office Hours
|
|
| 獲獎及補助情形 Awards and Grants |
|
|
| 聯合國永續發展目標 (SDGs跨域類別) Sustainable Development Goals, SDGs |
|
SDGs 03.
|
健康與福祉:確保及促進各年齡層健康生活與福祉 Good Health and Well-being:Ensure healthy lives and promote well-being for all at all ages.
|
|
SDGs 14.
|
保育海洋生態:保育及永續利用海洋生態系,以確保生物多樣性並防止海洋環境劣化 Life Below Water:Conserve and sustainably use the oceans, seas and marine resources for sustainable development
|
|
SDGs 15.
|
保育陸域生態:保育及永續利用陸域生態系,確保生物多樣性並防止土地劣化 Life on Land:Protect, restore and promote sustainable use of terrestrial ecosystems, sustainably manage forests, combat desertification, and halt biodiversity loss
|
|
|
課程目標 Learning Objectives
|
|
本課程為培養學生瞭解機器學習與人工智慧於環境與生態資料分析中的理論與應用能力。以理解機器學習理論基礎,熟悉監督學習方法,並應用於環境與生態資料分析。課程以案例導向方式進行物種分布建模、氣候驅動的族群動態預測、即時空氣品質監測、毒理與生態風險評估等,學生將學習處理大型資料集的能力,實踐跨領域整合思維,強化資料分析、模型建構與解釋能力
|
|
先修 ( 前置 ) 課程 Prerequisite
|
|
生態毒理學
|
| 彈性教學規劃 Flexible Teaching/Planning Schedules |
| *本課程實施16+2週彈性教學方案,其中第17、18週之彈性規劃如下: |
|
自主學習
|
|
|
課程大綱 Course Syllabus
|
| 週次 Week |
課程單元大綱 Unit |
教學方式 Instructional Method/Style/Teaching Style |
參考資料或相關作業 References or Related Materials |
評量方式 Grading |
|
1
|
Introduction and Overview
|
講授
|
|
課堂表現(含出席率)
|
|
2
|
Fundamentals in Machine Learning and Artificial Intelligence
|
講授
|
|
課堂表現(含出席率)
|
|
3
|
Environmental Dataset and Preprocessing
|
講授
|
|
課堂表現(含出席率)
|
|
4
|
Feature and target engineering
|
講授
|
|
課堂表現(含出席率)
|
|
5
|
Supervised learning I – Regression
|
講授
|
|
課堂表現(含出席率)
|
|
6
|
Supervised learning II – Classification
|
講授
|
|
課堂表現(含出席率)
|
|
7
|
Model Evaluation
|
講授/實作
|
|
作業撰寫
|
|
8
|
Deep Neural Network
|
講授
|
|
課堂表現(含出席率)
|
|
9
|
Midterm Project Proposal
|
講授/實作
|
|
個人書面報告
|
|
10
|
ML in Species Distribution
|
PBL
|
|
課堂表現(含出席率)
|
|
11
|
Climate-driven ML Model for Population Dynamics
|
PBL
|
|
課堂表現(含出席率)
|
|
12
|
ML in Quantitative Structure-Activity Relationship
|
PBL
|
|
課堂表現(含出席率)
|
|
13
|
IoT Data Analysis for Real-time Air Quality Prediction
|
PBL
|
|
課堂表現(含出席率)
|
|
14
|
ML in Absorption, Distribution, Metabolism, and Excretion
|
PBL
|
|
課堂表現(含出席率)
|
|
15
|
ML in Ecotoxicology
|
PBL
|
|
課堂表現(含出席率)
|
|
16
|
Group Project Presentations
|
PBL
|
|
課堂表現(含出席率)
|
|
17
|
AI Ethics
|
學生自主學習
|
|
觀察分析報告
|
|
18
|
Case study: AI in Environmental Research
|
學生自主學習
|
|
觀察分析報告
|
|
單一課程對應校能力指標程度 The Degree to Which Single Course Corresponds to School Competence
|
| 編號 No. |
校核心能力 School Core Competencies |
符合程度 Degree of conformity |
|
1
|
公民力 (Citizen)
|
1
|
|
2
|
自學力 (Self-learning)
|
5
|
|
3
|
資訊力 (Information)
|
5
|
|
4
|
創造力 (Creativity)
|
5
|
|
5
|
溝通力 (Communication)
|
3
|
|
6
|
就業力(Employability)
|
4
|
|
單一課程對應系能力指標程度 The Degree to Which Single Course Corresponds to Department Competence
|
| 編號 No. |
類別 Category |
系核心能力 Department Core Competencies |
符合程度 Degree of conformity |
|
01
|
系所
|
具備推廣與實施生態旅遊之基礎認知與執行力
|
3
|
|
02
|
系所
|
針對生態旅遊之特定議題具備深入探討分析之能力
|
3
|
|
03
|
系所
|
具備生態旅遊資源之田野調查,資料彙整之技能
|
5
|
|
04
|
系所
|
具備生態旅遊解說資料之編輯,撰寫與後製作之能力
|
5
|
|
05
|
系所
|
具備歸納分析生態旅遊研究文獻與調查資料之獨立作業能力
|
5
|
|
06
|
系所
|
有能力完成書面報告製作、口頭發表,以及論文寫作
|
5
|
|
單一課程對應院能力指標程度 The Degree to Which Single Course Corresponds to College Competence
|
| 編號 No. |
院核心能力 College Core Competencies |
符合程度 Degree of conformity |
|
1
|
語文能力
|
3
|
|
2
|
自主學習的能力
|
4
|
|
3
|
應用科技的能力
|
5
|
|
4
|
環境與生態專業知能
|
5
|
|
教科書或參考用書 Textbooks or Reference Books
|
|
館藏書名 Library Books
|
|
備註 Remarks
|
University of Cincinnati: Python Workshop Resources https://guides.libraries.uc.edu/c.php?g=222622&p=1473174
Bradley Boehmke, Brandon Greenwell. 2020. Hands-On Machine Learning with R. https://bradleyboehmke.github.io/HOML/
Aurélien Géron. 2022. Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow. 3nd Edition. O'Reilly Media, Inc. https://github.com/ageron/handson-ml2
OECD. 2014. Guidance Document on the Validation of (Quantitative) Structure-Activity Relationship [(Q)SAR] Models, OECD Series on Testing and Assessment, No. 69, OECD Publishing, Paris, https://doi.org/10.1787/9789264085442-en.
|
※請尊重智慧財產權,不得非法影印教科書※
※ Please respect intellectual property rights and do not illegally photocopy textbooks. ※
|
教學方法 Teaching Method
|
|
教學方法 Teaching Method
|
百分比 Percentage
|
|
講述
|
60 %
|
|
問題導向學習
|
25 %
|
|
專題實作
|
15 %
|
| 總和 Total |
100 % |
|
成績評量方式 Grading
|
| 評量方式 Grading |
百分比 Percentage |
|
個人書面報告
|
30 %
|
|
個人口頭報告
|
20 %
|
|
課堂參與
|
20 %
|
|
作業撰寫
|
30 %
|
| 總和 Total |
100 % |
|
課程大綱補充資料 Supplementary Material of Course Syllabus
|
|
|
|