Explainable Machine Learning for Scientific Insights and Discoveries
Open accessThe DOI matches its Crossref record; 135 of the 137 references it cites were found in a registry or an index.
Abstract
Machine learning methods have been remarkably successful for a wide range of application areas in the extraction of essential information from data. An exciting and relatively recent development is the uptake of machine learning in the natural sciences, where the major goal is to obtain novel scientific insights and discoveries from observational or simulated data. A prerequisite for obtaining a scientific outcome is domain knowledge, which is needed to gain explainability, but also to enhance scientific consistency. In this article, we review explainable machine learning in view of applications in the natural sciences and discuss three core elements that we identified as relevant in this context: transparency, interpretability, and explainability. With respect to these core elements, we provide a survey of recent scientific works that incorporate machine learning and the way that explainable machine learning is used in combination with domain knowledge from the application areas.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Several powerful AI algorithms are employing a so-called “black box” approach, where it is difficult or even impossible to understand how the obtained results have been achieved.66”
From Addressing bias in big data and AI for health care: A call for open science (2021) · cites this paper as [66]
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 1×
“image or a video. Lerer et al. [2016] and Li et al. [2016] use video simulations to learn intuitive physics, for example about the stability of wooden block towers. Lerer et al. [2016] use ResNet-34 [He et al., 2016] and Googlenet [Szegedy et al., 2015] to predict the fall of towers of wooden blocks, as well as DeepMa…”
MethodGradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · cited 1×
“o clips containing 101 objects of dierent characteristics, which was built for the task of deriving physical parameters such as velocity and mass. In their work, they use the LeNet CNN architecture [LeCun et al., 1998] to capture visual as well as physical characteristics while explicitly integrating physical laws bas…”
MethodGoing deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939778 · Cited by 17,555
Gaussian Processes for Machine Learning
Rasmussen, C. E., & Williams, C. K. I. (2005) · doi:10.7551/mitpress/3206.001.0001 · Cited by 11,705
(2016) · Cited by 11,679
Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)
Adadi, A., & Berrada, M. (2018) · IEEE Access · doi:10.1109/access.2018.2870052 · Cited by 6,294 · cited 1×
“Further details, types of interpretation, and specific realization can be found in recent surveys [7], [8], [20].”
BackgroundDeep learning and process understanding for data-driven Earth system science
Reichstein, M., Camps-Valls, G., Stevens, B., Jung, M., Denzler, J., Carvalhais, N., & Prabhat (2019) · Nature · doi:10.1038/s41586-019-0912-1 · Cited by 5,673
Lipton, Z. C. (2018) · Queue · doi:10.1145/3236386.3241340 · Cited by 5,427
Explanation in artificial intelligence: Insights from the social sciences
Miller, T. (2019) · Artificial Intelligence · doi:10.1016/j.artint.2018.07.007 · Cited by 5,302
Research works printed but not linked: 3
- 10.1037/0033-2909.110.3.499 · doi:10.1037/0033-2909.110.3.499 · Paper page
- frigg, 2018, Scientific representation, The Stanford Encyclopedia of Philosophy
- 10.1145/3233231 · doi:10.1145/3233231 · Paper page
Cited by
Items 801–900 of 999
Social physicsPreprint
Jusup, M., Holme, P., Kanazawa, K., Takayasu, M., Romić, I., Wang, Z., Geček, S., Lipić, T., Boris Podobnik, A., Wang, L., et al. (2021) · arXiv (Cornell University)
Wang, A., Mahmoud, M. S., Czasny, M., & Gurlo, A. (2021) · doi:10.33774/chemrxiv-2021-b8ncl
Sub-Setting Algorithm for Training Data Selection in Pattern RecognitionPreprint
Arwade, A., & Olafsson, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.06527
“Usually, models try to fit close to data to achieve high accuracy, but there is also a need to understand how the model operates and makes decisions [18].”
BackgroundPDTX: A novel local explainer based on the Perceptron Decision Tree
dos Santos, S. S., Alves, M. A., Ferreira, L. A., & Guimarães, F. G. (2021) · Congresso Brasileiro de Inteligência Computacional (CBIC) · doi:10.21528/cbic2021-50
“In [3], transparency is understood when the model that extracts parameters from the training data and generates labels for the test can be described and motivated by the model design.”
Background(2021) · Wiley eBooks · doi:10.1002/9781119646181.biblio
Betancourt, C., Stomberg, T. T., Edrich, A.-K., et al. (2022) · Geoscientific model development · doi:10.5194/gmd-2022-2-cec1
(2022) · Geoscientific model development · doi:10.5194/gmd-2022-2-rc1
Betancourt, C. (2022) · Geoscientific model development · doi:10.5194/gmd-2022-2-ac1
(2022) · Geoscientific model development · doi:10.5194/gmd-2022-2-rc2
Papacharalampous, G., & Tyralis, H. (2022) · Water · doi:10.3390/w14101657 · Cited by 19
Betancourt, C. (2022) · Geoscientific model development · doi:10.5194/gmd-2022-2-ac3
Betancourt, C. (2022) · Geoscientific model development · doi:10.5194/gmd-2022-2-ac2
(2021) · Earth system science data · doi:10.5194/essd-2020-380-rc1
(2021) · Earth system science data · doi:10.5194/essd-2020-380-rc2
Betancourt, C. (2021) · Earth system science data · doi:10.5194/essd-2020-380-ac1
Betancourt, C. (2021) · Earth system science data · doi:10.5194/essd-2020-380-ac2
Doctors in Medical Data Sciences: A New Curriculum (Preprint)Preprint
Cussat‐Blanc, S., Castets-Renard, C., & Monsarrat, P. (2021) · doi:10.2196/preprints.31290
Machine learning approaches in sleep and circadian research
Schade, M. M., Roberts, D. M., Honavar, V., & Buxton, O. M. (2022) · Elsevier eBooks · doi:10.1016/b978-0-12-822963-7.00383-2 · Cited by 1
NoGo VR Shooting Difficulty TaskPreprint
Pratiher, S., Sahoo, K. P., Acharya, M., Radhakrishnan, A., Alam, S., Kerick, S. E., Banerjee, N., Ghosh, N., & Patra, A. (2022) · doi:10.36227/techrxiv.21669248.v1 · Cited by 1
Yu, Z., Gan, Y., & Shen, Y. (2022) · International Journal for Multiscale Computational Engineering · doi:10.1615/intjmultcompeng.2022044133
Machine-Guided Design of Oxidation-Resistant Superconductors for Quantum Information Applications
Koppel, C., Wilfong, B., Iwanicki, A. G., Hedrick, E., Berry, T., & McQueen, T. M. (2023) · Inorganics · doi:10.3390/inorganics11030117 · Cited by 1
Automated Battery Power Fade Estimation for Fast Charge and Discharge Operations
Zarfati, E., & Bedogni, L. (2023) · IEEE Consumer Communications and Networking Conference · doi:10.1109/ccnc51644.2023.10060391
“[17] Fewer1 research focuses on power fading.”
Colangelo, G., Ribó, M., Montiel, E., Domínguez-Herrera, D., Olivé‐Gadea, M., Muchada, M., García‐Tornel, Á., Requena, M., Pagola, J., Juega, J., et al. (2023) · medRxiv · doi:10.1101/2023.03.24.23287721
“A criticism that emerges with the application of complex ML models is the “black box” effect 43 : even if the output of the ML model is very accurate, it may not be easily understandable, for instance in terms of the collection of features that have contributed to develop the algorithm 44 .”
Algorithm to Correct the Bigram Method to Identify an Author’s Text
Voronina, M. Y., Kislitsyn, A. A., & Orlov, Y. N. (2023) · Mathematical Models and Computer Simulations · doi:10.1134/s2070048223020175
“This definition clarifies, in terms of error estimation, the agreement adopted in [1] that explainable (interpretable, transparent) artificial intelligence is a machine learning method that can be called a white box, and it allows us to check which operations were carried out at which stages by the recognition algorit…”
BackgroundExplainability of Artificial Intelligence Models: Technical Foundations and Legal Principles
Laan, J. V. D. (2022) · Vietnamese Journal of Legal Sciences · doi:10.2478/vjls-2022-0006 · Cited by 3
Plan for Constructing DataDiscoveryLab: Creating DataBases for Well-Rounded SearchesPreprint
Keskinoglu, E. (2023) · Preprints.org · doi:10.20944/preprints202304.1074.v2
Focus on Multipath TCP: Introduction, Benefits and Future Research Trends
Ji, L., Ji, R., Wu, J., Gu, K., Jiang, F., & Cao, Y. (2021) · Research Briefs on Information and Communication Technology Evolution · doi:10.56801/rebicte.v7i.125
Prediction and interpretation of gamma pass rate based on SHAP value feature selectionPreprint
Ni, Q., Chen, L., Zhu, J., Pang, J., Wang, Z., & Yang, X. (2023) · Research Square · doi:10.21203/rs.3.rs-2974857/v1
Visual Analytics Tools for the Study of Complex Problems in Engineering and Biomedicine
Díaz, I., Enguita, J. M., Cuadrado, A. A., García-Pérez, D., & González, A. (2023) · IFIP advances in information and communication technology · doi:10.1007/978-3-031-34171-7_36
Huang, L., & Zhu, Q. (2023) · SpringerBriefs in computer science · doi:10.1007/978-3-031-30709-6_2
Subspace-Classification Approach for Simulated Tuple Class Assignment
Robila, V. I., & Haralick, R. M. (2023) · IEEE Long Island Systems, Applications and Technology Conference (LISAT) · doi:10.1109/lisat58403.2023.10179509
“The need for explainable approaches in sensitive fields is why subspace classification, another type of machine learning approach, can be beneficial and useful [8].”
BackgroundOn Responsibility for the Decisions of Robots and Complex Information Systems
Amelin, R. V., Milusheva, T., Tsybulevskaya, O., & Channov, S. (2023) · Lecture notes in networks and systems · doi:10.1007/978-3-031-36960-5_20
Challenges and future work directions in artificial intelligence with human-computer interaction
Panchal, M. H., & Panchal, S. (2023) · Elsevier eBooks · doi:10.1016/b978-0-323-99891-8.00006-1
Aziz, A. U. R. (2023) · Academic Journal of Nawroz University · doi:10.25007/ajnu.v1n1a1936 · Cited by 1
Risce- An Explainable ML Chain for Practical Sustainable Agriculture
Karmakar, C., Bhowmik, A., Dumitru, C. O., & Datcu, M. P. (2023) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss52108.2023.10282452
Bridging the Interpretability Gap in Coupled Neural Dynamical Models
Xiang, M., Luo, W., Hou, J., & Tao, W. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-46661-8_35
Principle of learning sign rules by neural networks in qubit lattice models
Cao, J., Hu, S., Yin, Z., & Xia, K. (2023) · Physical review. B./Physical review. B · doi:10.1103/physrevb.108.195127 · Cited by 1
Perspectives and Final Remarks
Giraldi, G. A., de Almeida, L. R., Apolinário, A. L., & da Silva, L. T. (2023) · SpringerBriefs in mathematics · doi:10.1007/978-3-031-42333-8_9
Explainable Machine Learning Models for Corn Yield Prediction Using Uav Multispectral DataPreprint
Kumar, C., Dhillon, J. S., Huang, Y., & Reddy, K. N. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4674762
Liu, L., Zhou, F., & Cao, W. D. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4682589
Revisiting Cylindrical Buckling under Axial Compression using Explainable Machine Learning
Wafi, M. G., Palar, P. S., Robani, M. D., Jusuf, A., Lavi, Z., & Morlier, J. (2024) · AIAA SciTech Forum · doi:10.2514/6.2024-0265
An Example of Ontology in Medical Diagnosis: A Case Study
Prnjak, A., Rosić, M., Zaharija, G., Krpan, D., & Mladenović, M. (2024) · Communications in computer and information science · doi:10.1007/978-3-031-53025-8_14
Explainable data stream mining: Why the new models are better
Hu, H., Kantardzic, M. M., & Kar, S. (2024) · Intelligent Decision Technologies · doi:10.3233/idt-230065 · Cited by 1
“Existing state-of-the-art studies on Explainable Machine Learning focus on providing explanations for static learning models [4,5].”
Guan, S., & Loew, M. H. (2023) · IEEE Applied Imagery Pattern Recognition Workshop · doi:10.1109/aipr60534.2023.10440662
“To comprehensively understand the mechanisms of neural network (NN) models and to explain their output results, however, still require more basic research [1].”
MethodResultOn Robustness of the Explanatory Power of Machine Learning ModelsPreprint
Panigrahi, B., Razavi, S., Doig, L. E., Cordell, B., Gupta, H. V., & Liber, K. (2024) · doi:10.22541/essoar.171052510.02996233/v1
Machine Learning and the Secure Access Service Edge
Wright, S. A., Sathyagiri, A., & Tayal, R. (2023) · Congress in Computer Science, Computer Engineering, and Applied Computing (CSCE) · doi:10.1109/csce60160.2023.00367
Correr, G. I. (2024) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/d.76.2024.tde-24042024-083735
Hampel-Arias, Z., Carr, A., Klein, N., & FLYNN, E. B. (2024) · IEEE Southwest Symposium on Image Analysis and Interpretation (SSIAI) · doi:10.1109/ssiai59505.2024.10508608 · Cited by 2
“[11] and references therein) and code libraries [12, 13] have arisen to gain better insight into why machine learning models make their predictions.”
BackgroundSynthesizing the Born rule with reinforcement learning
Piera, R. S., DeBrota, J. B., Weiss, M. B., Lemos, G. B., Araújo, J. S., Aguilar, G. H., & Pienaar, J. (2025) · Physical Review Research · doi:10.1103/physrevresearch.7.033042 · Cited by 1
Understanding Local Government Responsible Ai Strategy: Review of Municipal Policy DocumentsPreprint
David, A., Yiğitcanlar, T., Desouza, K. C., Li, Y. L., Cheong, P. H., Mehmood, R., & Corchado, J. M. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4829216
Taxonomy for federated learning in digital healthcare systems
Udeji, F., Sur, S. N., Kumaravelu, V. B., & Kavitha, K. V. N. (2024) · Elsevier eBooks · doi:10.1016/b978-0-443-13897-3.00008-4
Predisposing Factors of Vaginal Discharge in Pregnant Women in the Coastal Area of Bengkulu City
Agni, S. O., Dewiani, K., Versita, R., Novianti, & Yulyani, L. (2024) · Journal of Public Health Sciences · doi:10.56741/jphs.v3i01.471
“Apart from that, a piece also affects a person's purchasing power, so they can obtain more sources of information to increase their insight and knowledge [21].”
BackgroundSeasonal variation in mortality in Brazil
Almeida, V. (2024) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/d.45.2024.tde-29082024-121102
Liu, Y., Wang, X., Song, Y., Wang, B., & Du, D. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3409567
“They often struggle to generalize to unseen regions of the state space [5], [6].”
Niederländer, M., Biswas, R., Mutz, M., Limbachiya, D., & Werth, D. (2024) · E3S Web of Conferences · doi:10.1051/e3sconf/202456601007
Gull, C. Q., Aguilar, J., & García, R. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10651500
“The implementation and use of machine learning methods is of increasing importance today, because there are different applications in the real world, for example, in medicine, in industry, in academia, in others [1], [2].”
BackgroundFunction Search Automated by Evolutionary Machine Learning
Shmalko, E. Y., Diveev, A., & Gromov, I. Y. (2024) · International Conference on Control, Decision and Information Technologies (CoDIT) · doi:10.1109/codit62066.2024.10708558
“Today, machine learning methods for finding functions have gained immense popularity [4] due to the versatility of the approach.”
BackgroundNeurocomputing Advancements to Unlock Image Intelligence for Industrial Computer Vision
Saha, S., Lilhore, U. K., & Simaiya, S. (2024) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3693-6303-4.ch013
Combinatorial Behavioural Phenotyping of Mouse Models of Schizophrenia
Lipina, T. V. (2024) · Royal Society of Chemistry eBooks · doi:10.1039/9781837672059-00031
Hu, L., Wang, Y., Sun, C., He, Y., Fan, Y., Su, S., Hou, L., Zheng, Y., & Chen, J. (2024) · Research Square · doi:10.21203/rs.3.rs-5449928/v1
Re-envisioning Investment Priorities
Dent, D. (2024) · Springer eBooks · doi:10.1007/978-3-031-75216-2_7
Yu, D., Wang, Q., Yang, S., & Wang, C. (2024) · Lecture notes in networks and systems · doi:10.1007/978-3-031-77571-0_84
AI-Assisted Design-Space Analysis of High-Performance Arm Processors
Moore, J., Deakin, T., & McIntosh‐Smith, S. (2024) · International Conference for High Performance Computing, Networking, Storage and Analysis (SC) · doi:10.1109/scw63240.2024.00186
“This approach has previously been explored in other domains for both neural networks and traditional ML [20], though this paper expands on the prior work implementing models in microarchitectural design with the use of a more modern parameter space and a more expansive search, training our model…”
A fast numerical integration scheme for clonal expansion processes on graphs
Paterson, C., Gao, M., Hellier, J., Luebeck, E. G., Wedge, D. C., & Božić, I. (2026) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1012784 · Cited by 1
Eris, S. B., Bozkurt, M. R., Eris, O., & Bílgín, C. (2025) · IEEE Access · doi:10.1109/access.2025.3531501 · Cited by 3
LESI-GNN: An Interpretable Graph Neural Network Based on Local Structures Embedding
Minello, G., Zhang, L.-C., Bicciato, A., Rossi, L., Andrea Torsello, A., & Cosmo, L. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-80507-3_8
Laudanski, A. F., Küderle, A., Kluge, F., Eskofier, B. M., & Acker, S. M. (2025) · Sensors · doi:10.3390/s25041083 · Cited by 1
“While many machine learning-based approaches can be applied to the classification of human motion, several of these utilize deep learning to map connections between inputs and outputs through what is colloquially referred to as a “black box” [44].”
Partial Dependence Plots and Data-Driven Surrogates for Aerodynamic Analysis of Airfoil Databases
Palar, P. S., Dwianto, Y. B., Shimoyama, K., Obayashi, S., & Zuhal, L. R. (2025) · AIAA SciTech Forum · doi:10.2514/6.2025-2808
SMT-EX: An Explainable Surrogate Modeling Toolbox for Mixed-Variables Design Exploration
Robani, M. D., Palar, P. S., Zuhal, L. R., Saves, P., & Morlier, J. (2025) · AIAA SciTech Forum · doi:10.2514/6.2025-0777 · Cited by 7
“To that end, explainability serves as a powerful means to “dissect” the input-output relationship and provide knowledge to the user [17–19].”
Leveraging AI for Intelligent Oilfield Development: A Pathway to Digital TransformationPreprint
Aalhusaini, T. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5073392
Javed, A., Shoaib, M., Jaleel, A., Deriche, M. A., & Nawaz, S. (2025) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2025.057359 · Cited by 1
“Explainability in web-based sentiment analysis systems includes high computation costs [8], sophisticated model interpretation [9], problems of scalability, and design variations for individual users [10–12].”
Uncertainty-aware Unsupervised Machine Learning to Draw Coastline
Karmakar, C., Gottschling, N. M., Camero, A., & Datcu, M. (2024) · Advanced Topics on Measurement and Simulation (ATOMS) · doi:10.1109/atoms60779.2024.10921503
Subramanian, V. (2025) · Wiley eBooks · doi:10.1002/9781394155408.ch19
Bauckhage, C., Schulz, D., & von Rueden, L. (2025) · Cognitive technologies · doi:10.1007/978-3-031-83097-6_1
Arantes, M., González–Manteiga, W., Torres, J., Pinto, A., Departamento de Estadística, A. M. Y. O., CITMAga: Centro de Investigación e Tecnoloxía Matemática de Galicia, S. D. C., Departamento de Matemática Aplicada, U. D. V., & LIAAD - INESC TEC, P. 4.-9. (2025) · Electronic Research Archive · doi:10.3934/era.2025092 · Cited by 1
Zhou, H., Zheng, Y., Hu, Y., Zhang, S., Guo, W., Tai, Y., Feng, Y., Wang, Y., & Pan, H. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5245681
Thu, M. K., Shibayama, S., & Yarime, M. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5246432
Wang, Y., Ma, X., Robson, A., Short, R. D., & Bradley, J. W. (2025) · Plasma Processes and Polymers · doi:10.1002/ppap.70035 · Cited by 1
“Machine learning (ML), a branch of artificial intelligence, has revolutionized scientific research by demonstrating exceptional performance, particularly when provided with labeled data [22, 23], which is called supervised ML.”
Combining Self-Attention and Dilation Convolutional for Semantic Segmentation of Coal Maceral Groups
Xi, Z., Lv, Z., Zheng, Y., Liu, X., Yu, Z., Chen, J., Hu, J., & Liu, Y. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3568884
“However,these traditional machine learning approaches require the substantial amount of domain knowledge and experience [21], [22], which not only leads to models often having high computational complexity, but also requires time-consuming and laborious professional annotation of a large number of…”
Explainability of Review Rating Prediction for M-Government Apps in Saudi Arabia
Radain, D., Alahmadi, D. H., & Wali, A. M. (2024) · IEEE International Conference on Computing, Engineering and Design (ICCED) · doi:10.1109/icced64257.2024.10982853
“As a result, the explainability of these models has emerged as a crucial prerequisite for approving and trusting their decisions [11].”
author, & Singh, A. M. (2025) · INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT · doi:10.55041/ijsrem48086
Singh, R. R., Singh, B. K., Atrey, K., & Bodhey, N. K. (2025) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3693-9846-3.ch004
Machine Learning and UASs for Managing Autumn Olive (Elaeagnus umbellata) on Reclaimed Surface Mines
Keane, S. M. (2025) · The Research Repository @ WVU (West Virginia University) · doi:10.33915/etd.12839
Santhiya, C., Lavanya, R., Chakkaravarthy, G. V., Indira, K., Subashini, S., & Mohammed Fayaz, A. (2025) · International Conference on Computational Robotics, Testing and Engineering Evaluation (ICCRTEE) · doi:10.1109/iccrtee64519.2025.11052857
(2025) · Elsevier eBooks · doi:10.1016/b978-0-323-91649-3.16001-0
MPD Event Detection, Automation and Control
van Oort, E. (2025) · Elsevier eBooks · doi:10.1016/b978-0-323-91649-3.00005-8
Automatic Piecewise Linear Regression for Predicting Student Learning Satisfaction
Choi, H., & Nadarajan, G. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-98284-2_6 · Cited by 1
“The field of trustworthy Artificial Intelligence has garnered a fair amount of attention recently [17, 29].”
Bralet, A., Atto, A. M., Chanussot, J., & Trouvé, E. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3595267
“To balance this debate and improve the confidence in neural networks, recent researches propose explanation or interpretation strategies [25].”
Theory-Driven Deep Learning: Methods and Insights for Training Neural NetworksPreprint
Nasir, K., & Reva, A. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5341247
Convergence among inflation, growth, and exchange rate: North African evidencePreprint
Fadol, H. T. A. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5384314
Convergence Among Inflation, Growth, and Exchange Rate: North African EvidencePreprint
Fadol, H. T. A. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5384395
Mathieu, J.-P., Kronwitter, S., Pfahler, J., Roberto, M. D., & Vielhaber, M. (2025) · Proceedings of the Design Society · doi:10.1017/pds.2025.10168 · Cited by 1
“However, xAI techniques serve to gain transparency of the trained ML model, whereby explainability is only achieved by including domain knowledge (Roscher et al., 2020).”
Human Activity Recognition Using Machine Learning
Tiwari, M., & Gupta, P. (2025) · Communications in computer and information science · doi:10.1007/978-3-032-00793-3_12
Challenges, opportunities, and future of machine learning in membrane technology
Mustafa, K., Rezakazemi, M., & Mahboob, R. M. M. (2025) · Elsevier eBooks · doi:10.1016/b978-0-443-27422-0.00006-2
Liu, Z., Liu, Y.-L., Yeh, W., & Huang, C. (2025) · Computer Science and Information Systems · doi:10.2298/csis241130068l
“• Explainability : The definition of this element varies [36], but it is commonly understood as the user’s ability to explain why the model made a specific decision, understand the rationale behind a particular prediction, and even integrate domain knowledge with the prediction to provide…”
InfluentialGlobal Properties from Local Explanations with Concept Explanation Clusters
Haedecke, E., Akila, M., & von Rueden, L. (2025) · Communications in computer and information science · doi:10.1007/978-3-032-08317-3_1 · Cited by 1
The gap matters: An explainable customer dissatisfaction tracing analysis
Shi, X., Wei, Q., & Chen, G. (2025) · Information & Management · doi:10.1016/j.im.2025.104267 · Cited by 3
Feedback control to prevent or delay transition in two-dimensional parallel shear flows
Carlier, J., & Collewet, C. (2025) · Physical Review Fluids · doi:10.1103/vs7y-8b3p
Metadata
- Authors
- Roscher, R., Bohn, B., Duarte, M. F., & Garcke, J.
- Affiliations
- University of Bonn (DE)
- University of Massachusetts Amherst (US)
- Venue
- IEEE Access
- Published
- 2020
- Volume
- 8
- Pages
- 42200-42216
- ISSN
- 2169-3536 (ISSN-L)
- OpenAlex
- W2945526235
- Cited by
- 1,040
- References
- 137
- Citations by year
- 2026: 152 · 2025: 178 · 2024: 168 · 2023: 184 · 2022: 174 · 2021: 130 · 2020: 47
- FWCI
- 52.58
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- IEEE Access (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Publikationsdatenbank der Fraunhofer-Gesellschaft (Fraunhofer-Gesellschaft) (submittedVersion, other-oa)
- Fraunhofer-Publica (Fraunhofer-Gesellschaft) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Fraunhofer Cluster of Excellence Cognitive Internet Technologies
- Deutsche Forschungsgemeinschaft
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Social Sciences › Decision Sciences › Information Systems and Management › Scientific Computing and Data Management
- Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science
- Keywords
- explainable machine learning, scientific discovery, transparency, interpretability, explainability, domain knowledge, observational data, simulated data
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.