More Like this

1. Landslide susceptibility modeling by interpretable neural network

   https://doi.org/10.1038/s43247-023-00806-5  

   Youssef, K.; Shao, K.; Moon, S.; Bouchard, L.-S. (December 2023, Communications Earth & Environment)

   Abstract Landslides are notoriously difficult to predict because numerous spatially and temporally varying factors contribute to slope stability. Artificial neural networks (ANN) have been shown to improve prediction accuracy but are largely uninterpretable. Here we introduce an additive ANN optimization framework to assess landslide susceptibility, as well as dataset division and outcome interpretation techniques. We refer to our approach, which features full interpretability, high accuracy, high generalizability and low model complexity, as superposable neural network (SNN) optimization. We validate our approach by training models on landslide inventories from three different easternmost Himalaya regions. Our SNN outperformed physically-based and statistical models and achieved similar performance to state-of-the-art deep neural networks. The SNN models found the product of slope and precipitation and hillslope aspect to be important primary contributors to high landslide susceptibility, which highlights the importance of strong slope-climate couplings, along with microclimates, on landslide occurrences. 

   more » « less
2. Advancing Computational Toxicology by Interpretable Machine Learning

   https://doi.org/10.1021/acs.est.3c00653  

   Jia, Xuelian; Wang, Tong; Zhu, Hao (May 2023, Environmental Science & Technology)
3. Towards Interpretable Object Detection by Unfolding Latent Structures

   Wu, Tianfu; Song, Xi (October 2019, IEEE International Conference on Computer Vision)

   This paper first proposes a method of formulating model interpretability in visual understanding tasks based on the idea of unfolding latent structures. It then presents a case study in object detection using popular two-stage region-based convolutional neural network (i.e., R-CNN) detection systems. The proposed method focuses on weakly-supervised extractive rationale generation, that is learning to unfold latent discriminative part configurations of object instances automatically and simultaneously in detection without using any supervision for part configurations. It utilizes a top-down hierarchical and compositional grammar model embedded in a directed acyclic AND-OR Graph (AOG) to explore and unfold the space of latent part configurations of regions of interest (RoIs). It presents an AOGParsing operator that seamlessly integrates with the RoIPooling /RoIAlign operator widely used in R-CNN and is trained end-to-end. In object detection, a bounding box is interpreted by the best parse tree derived from the AOG on-the-fly, which is treated as the qualitatively extractive rationale generated for interpreting detection. In experiments, Faster R-CNN is used to test the proposed method on the PASCAL VOC 2007 and the COCO 2017 object detection datasets. The experimental results show that the proposed method can compute promising latent structures without hurting the performance. 

   more » « less
4. LILO: Learning interpretable libraries by compressing and documenting code

   Grand, Gabriel; Wong, Lionel; Bowers, Maddy; Olausson, Theo; Liu, Muxin; Tenenbaum, Joshua; Andreas, Jacob (May 2024, International Conference on Learning Representations)
5. Accurate virus identification with interpretable Raman signatures by machine learning

   https://doi.org/10.1073/pnas.2118836119  

   Ye, Jiarong; Yeh, Yin-Ting; Xue, Yuan; Wang, Ziyang; Zhang, Na; Liu, He; Zhang, Kunyan; Ricker, RyeAnne; Yu, Zhuohang; Roder, Allison; et al (June 2022, Proceedings of the National Academy of Sciences)

   Rapid identification of newly emerging or circulating viruses is an important first step toward managing the public health response to potential outbreaks. A portable virus capture device, coupled with label-free Raman spectroscopy, holds the promise of fast detection by rapidly obtaining the Raman signature of a virus followed by a machine learning (ML) approach applied to recognize the virus based on its Raman spectrum, which is used as a fingerprint. We present such an ML approach for analyzing Raman spectra of human and avian viruses. A convolutional neural network (CNN) classifier specifically designed for spectral data achieves very high accuracy for a variety of virus type or subtype identification tasks. In particular, it achieves 99% accuracy for classifying influenza virus type A versus type B, 96% accuracy for classifying four subtypes of influenza A, 95% accuracy for differentiating enveloped and nonenveloped viruses, and 99% accuracy for differentiating avian coronavirus (infectious bronchitis virus [IBV]) from other avian viruses. Furthermore, interpretation of neural net responses in the trained CNN model using a full-gradient algorithm highlights Raman spectral ranges that are most important to virus identification. By correlating ML-selected salient Raman ranges with the signature ranges of known biomolecules and chemical functional groups—for example, amide, amino acid, and carboxylic acid—we verify that our ML model effectively recognizes the Raman signatures of proteins, lipids, and other vital functional groups present in different viruses and uses a weighted combination of these signatures to identify viruses. 

   more » « less