AI explainability framework for environmental management research

被引：27

作者：

Arashpour, Mehrdad ^{[1
]}

机构：

[1] Monash Univ, Dept Civil Engn, Melbourne, Vic 3800, Australia

来源：

JOURNAL OF ENVIRONMENTAL MANAGEMENT | 2023年 / 342卷

基金：

澳大利亚研究理事会;

关键词：

Environmental crisis; Environmental management research; Explainable AI (XAI); Management and valorization of solid waste; Multimodal and generative pre-trained trans-formers; Responsible and fair artificial intelligence; Vision-language deep learning models;

D O I：

10.1016/j.jenvman.2023.118149

中图分类号：

X [环境科学、安全科学];

学科分类号：

08 ; 0830 ;

摘要：

Deep learning networks powered by AI are essential predictive tools relying on image data availability and processing hardware advancements. However, little attention has been paid to explainable AI (XAI) in appli- cation fields, including environmental management. This study develops an explainability framework with a triadic structure to focus on input, AI model and output. The framework provides three main contributions. (1) A context-based augmentation of input data to maximize generalizability and minimize overfitting. (2) A direct monitoring of AI model layers and parameters to use leaner (lighter) networks suitable for edge device deployment, (3) An output explanation procedure focusing on interpretability and robustness of predictive de- cisions by AI networks. These contributions significantly advance state of the art in XAI for environmental management research, offering implications for improved understanding and utilization of AI networks in this field.

引用

页数：7

共 36 条

[11] Deep Residual Learning for Image Recognition [J].

He, Kaiming ;

Zhang, Xiangyu ;

Ren, Shaoqing ;

Sun, Jian .

2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :770-778

[12]

Hendrycks D, 2020, Arxiv, DOI arXiv:1912.02781

[13]

Goodfellow IJ, 2015, Arxiv, DOI arXiv:1412.6572

[14]

Krechetov I.V., 2018, J ENV MANAG TOURISM, V9, P1805, DOI [10.14505/jemt.v9.8(32).21, DOI 10.14505/JEMT.V9.8(32).21]

[15] ImageNet Classification with Deep Convolutional Neural Networks [J].

Krizhevsky, Alex ;

Sutskever, Ilya ;

Hinton, Geoffrey E. .

COMMUNICATIONS OF THE ACM, 2017, 60 (06) :84-90

[16]

Krizhevsky Alex, 2009, Learning multiple layers of features from tiny images

[17] Neural Network Analysis for Microplastic Segmentation [J].

Lee, Gwanghee ;

Jhang, Kyoungson .

SENSORS, 2021, 21 (21)

[18] Estimation of municipal solid waste amount based on one-dimension convolutional neural network and long short-term memory with attention mechanism model: A case study of Shanghai [J].

Lin, Kunsen ;

Zhao, Youcai ;

Tian, Lu ;

Zhao, Chunlong ;

Zhang, Meilan ;

Zhou, Tao .

SCIENCE OF THE TOTAL ENVIRONMENT, 2021, 791

[19] A ConvNet for the 2020s [J].

Liu, Zhuang ;

Mao, Hanzi ;

Wu, Chao-Yuan ;

Feichtenhofer, Christoph ;

Darrell, Trevor ;

Xie, Saining .

2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2022, :11966-11976

[20]

Lundberg SM, 2017, ADV NEUR IN, V30

← 1 2 3 4 →