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 501–600 of 999
Self-Supervised Pretraining With Monocular Height Estimation for Semantic Segmentation
Xiong, Z., Chen, S., Shi, Y., & Zhu, X. X. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3412629 · Cited by 10
“Many researchers focused on saliency-based and attribution-based methods [12], [25], [26] for explainable deep networks.”
BackgroundMethodEthics in climate AI: From theory to practice
Acquaviva, V., Barnes, E. A., Gagne, D. J., McKinley, G. A., & Thais, S. J. (2024) · PLOS Climate · doi:10.1371/journal.pclm.0000465 · Cited by 11
Deep Learning for Generating Phase-Conditioned Infrared Spectra
Na, G. S. (2024) · Analytical Chemistry · doi:10.1021/acs.analchem.4c04786 · Cited by 9
Economic well-being assessment: a review of traditional and remote sensing approaches
Wang, L., Long, T., Jiang, W. J., Adam, E., Wen, C., Jiao, W., & He, G. (2025) · International Journal of Digital Earth · doi:10.1080/17538947.2025.2504137 · Cited by 10
“Future efforts should focus on developing and implementing model visualization and interpretation tools (Roscher et al. 2020) to enhance the transparency and interpretability of model predictions, fostering trust, and facilitating the translation of insights into actionable policies.”
Kierdorf, J., Garcke, J., Behley, J., Cheeseman, T., & Roscher, R. (2020) · ISPRS annals of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-annals-v-2-2020-1005-2020 · Cited by 8
“These tools are extremely helpful, but have only recently been used to derive new scientific knowledge and discoveries, and to improve the learned model (Schramowski et al., 2020, Roscher et al., 2020).”
BackgroundSelf-citationEmergence of a finite-size-scaling function in the supervised learning of the Ising phase transition
Kim, D., & Kim, D. (2021) · Journal of Statistical Mechanics Theory and Experiment · doi:10.1088/1742-5468/abdc18 · Cited by 10
Testing Federated Learning on Health and Wellbeing Data
Mocanu, I. G., Smădu, R.-A., Drăgoi, M., Mocanu, A., & Cramariuc, O. T. (2021) · E-Health and Bioengineering Conference (EHB) · doi:10.1109/ehb52898.2021.9657698 · Cited by 6
Research on Intelligent Bodybuilding System Based on Machine Learning
Chen, C. (2022) · Journal of Sensors · doi:10.1155/2022/6293856 · Cited by 6
“This phenomenon is caused by the attitude module’s own way of calculating angles, but it can have a negative effect on the period calculation, so the three angular axes should be excluded from the selection of the sensitive axes [32].”
BackgroundRetractedInterpretability of Machine Learning-Based Results of Malware Detection Using a Set of Rules
Dolejš, J., & Jureček, M. (2022) · Advances in information security · doi:10.1007/978-3-030-97087-1_5 · Cited by 8
Policy regularization for legible behavior
Persiani, M., & Hellström, T. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-07942-7 · Cited by 8
“This can be achieved firstly by translating the classifiers’ latent features responsible for its decisions into a space that is interpretable, and then compute explanations on that space [17].”
BackgroundRivera, A. J., Muñoz, J. C., Pérez-Godoy, M. D., Pedro, B. S. D. S., Charte, F., Elizondo, D. A., Rodríguez, C., Abolafia, M. L., Perea, A., & del Jesús, M. J. (2023) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2023.102494 · Cited by 6
McDonnell, K. J. (2023) · Journal of Clinical Medicine · doi:10.3390/jcm12144830 · Cited by 12
Causal Discovery and Knowledge Injection for Contestable Neural Networks
Russo, F., & Toni, F. (2023) · Frontiers in artificial intelligence and applications · doi:10.3233/faia230495 · Cited by 18
“It has been shown to lead, amongst others, to less data need, improved generalisation [3] and interpretability [25].”
BackgroundYour Battery Is a Blast! Safeguarding Against Counterfeit Batteries with Authentication
Marchiori, F., & Conti, M. (2023) · ACM SIGSAC Conference on Computer and Communications Security (CCS) · doi:10.1145/3576915.3623179 · Cited by 8
“To confirm our hypothesis, we use Explainable Machine Learning (XAI) techniques on the ML models that we previously trained [55].”
MethodUser Purchase Intention Prediction Based on Improved Deep Forest
Zhang, Y., Yu, Q., & Zhang, L. (2023) · Computer Modeling in Engineering & Sciences · doi:10.32604/cmes.2023.044255 · Cited by 6
Pathway toward prior knowledge-integrated machine learning in engineering
Chen, X., & Geyer, P. (2023) · Building Simulation Conference proceedings · doi:10.26868/25222708.2023.1481 · Cited by 9
Pütz, S., Ashhab, H. E., Hertel, M., Mikut, R., Götz, M., Hagenmeyer, V., & Schäfer, B. (2024) · ACM International Conference on Future Energy Systems (e-Energy) · doi:10.1145/3632775.3661963 · Cited by 7
“Moreover, the interpretability of the algorithms also helps in gaining scientific insights and informed decision-making [30].”
BackgroundMachine learning in agricultural economics
Baylis, K., Heckelei, T., & Storm, H. (2021) · Handbook of agricultural economics · doi:10.1016/bs.hesagr.2021.10.007 · Cited by 12
Automatic shooting detection in archery from acceleration data for score prediction
Ogasawara, T., Fukamachi, H., Aoyagi, K., Kumano, S., Togo, H., Oka, K., & Yamaguchi, M. (2023) · Sports Engineering · doi:10.1007/s12283-023-00402-y · Cited by 11
“However, we used 1584 samples for shooting detection in this study, suggesting that the number of participants were sufficient, and an SVM has been reported to suffice with only some dozens of examples in an archery dataset [10].”
MethodMedical operational AI: artificial intelligence in routine medical operations
Berns, F., Heilig, N., Stumpe, F., & Kirchhoff, J. (2023) · Journal of Laboratory Medicine · doi:10.1515/labmed-2023-0011 · Cited by 5
Human In Command Machine Learning
Holmberg, L. (2021) · doi:10.24834/isbn.9789178771875 · Cited by 10
An AI Management Model for the Manufacturing Industry - AIMM
Biegel, T., Cassoli, B. B., Hoffmann, F., Jourdan, N., & Metternich, J. (2021) · TUbilio (Technical University of Darmstadt) · doi:10.26083/tuprints-00019038 · Cited by 6
“Case studies in which domain knowledge was used in the AI project emphasize its importance for validating and improving the results of the analysis [26].”
Czajkowski, M., Jurczuk, K., & Krętowski, M. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.127131 · Cited by 6
Yu, G., Wang, C., Zhuo, Q., Wang, Z., & Huang, M. (2025) · Waste Management · doi:10.1016/j.wasman.2025.114903 · Cited by 5
Review on Artificial Intelligence in the Environmental Monitoring
Chauhan, B. V. S., Vedrtnam, A., Wyche, K. P., & Verma, S. (2025) · Springer eBooks · doi:10.1007/978-981-96-6863-2_2 · Cited by 13
He, X., Yuan, Q., Qin, Y., & Lu, J. (2025) · Environmental Development · doi:10.1016/j.envdev.2025.101298 · Cited by 6
Glaws, A., Schall, J., Ballen, A., Louks, A. E., Davis, K. O., Palmstrom, A. F., Ugirumurera, J., & Kern, D. B. (2025) · Energy and AI · doi:10.1016/j.egyai.2025.100640 · Cited by 6
Alarcon, G. M., & Capiola, A. (2025) · Frontiers in Computer Science · doi:10.3389/fcomp.2025.1662185 · Cited by 13
Zhu, Y., Tang, H., Pan, Y., Ouyang, P., Ma, Y., & Xu, K. (2025) · IEEE Transactions on Electron Devices · doi:10.1109/ted.2025.3588137 · Cited by 5
“In addition, incorporating explainability techniques may enhance the interpretability of learned models, making them more transparent and trustworthy for use in semiconductor process engineering [30].”
MobileNetV3–Transformer-Based Prediction of Highway Accident Severity
Liang, C., Wei, J., Wang, G., Yang, X., & Qin, L. (2025) · Applied Sciences · doi:10.3390/app152312694 · Cited by 5
Comparison of generalised additive models and neural networks in applications: A systematic review
Doohan, J., Kook, L., & Burke, K. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.131082 · Cited by 10
Rahman, M. M., Calhoun, V. D., & Plis, S. (2026) · Imaging Neuroscience · doi:10.1162/imag.a.1129 · Cited by 16
Pontiveros, M. J., Solano, G. A., Tee, C., & Tee, M. L. (2020) · International Conference on Information, Intelligence, Systems & Applications (IISA) · doi:10.1109/iisa50023.2020.9284372 · Cited by 5
“[16] defined explanation in the context of machine learning as a collection of features that have contributed for a particular example to produce a decision (i.”
BackgroundLee, S. B. (2024) · JAMIA Open · doi:10.1093/jamiaopen/ooae035 · Cited by 6
“51 This study’s approach to studying thematic elements of architecture could be a different paradigm for studying ML behavior and help us achieve a higher level of understanding how ML functions.”
BackgroundGong, R., Zhang, H., Lu, X., Wan, H., Zhang, Y., Luo, X., Zhang, J., & Xie, R. (2024) · PLoS ONE · doi:10.1371/journal.pone.0299362 · Cited by 5
Practical Trainable Temporal Postprocessor for Multistate Quantum Measurement
Khan, S. A., Kaufman, R., Mesits, B., Hatridge, M. J., & Türeci, H. E. (2024) · PRX Quantum · doi:10.1103/prxquantum.5.020364 · Cited by 7
“Neverthe-less, we introduce a simplified theoretical model of dispersive qubit-cavity systems below, to erect a foundation for the interpretability of TPP [40].”
BackgroundUncertainty Quantification of Satellite-Based Essential Climate Variables Derived from Deep Learning
Gou, J., Salberg, A.-B., Shahvandi, M. K., Tourian, M. J., Meyer, U., Boergens, E., Waldeland, A. U., Velicogna, I., Dahl, F., Jäggi, A., et al. (2026) · Surveys in Geophysics · doi:10.1007/s10712-025-09919-2 · Cited by 13
Adeli, A., Dastgheib, A., & Roelvink, D. (2025) · Frontiers in Marine Science · doi:10.3389/fmars.2025.1562504 · Cited by 5
Coronel, J. C., Sweitzer, M. D., Bonus, J. A., Dore, R. A., & Lerner, B. (2025) · Journal of Communication · doi:10.1093/joc/jqaf036 · Cited by 7
Explainable Earth Surface Forecasting Under Extreme Events
Pellicer-Valero, Ó. J., Fernández‐Torres, M., Ji, C., Mahecha, M. D., & Camps‐Valls, G. (2025) · Earth s Future · doi:10.1029/2024ef005446 · Cited by 10
“The field of xAI was therefore born to make them interpretable (i.e., help us understand their decisions) and explainable (i.e., link these interpretations to domain knowledge) [24].”
Development and Assessment of Physics-guided Machine Learning Framework for Prognosis System.
Gurgen, A. (2021) · NCSU Libraries Repository (North Carolina State University Libraries) · Cited by 6
Tetrahedron equation: algebra, topology, and integrability
Talalaev, D. V. (2021) · Russian Mathematical Surveys · doi:10.4213/rm10009 · Cited by 16
Demystifying Drug Repurposing Domain Comprehension with Knowledge Graph Embedding
Ramalli, E., Parravicini, A., Donato, G. W. D., Salaris, M., Hudelot, C., & Santambrogio, M. D. (2021) · IEEE Biomedical Circuits and Systems Conference (BioCAS) · doi:10.1109/biocas49922.2021.9644981 · Cited by 5
Advances in Integrated High-Throughput and Phenomics Application in Plants and Agriculture
Waseem, M., Shaheen, I., & Aslam, M. M. (2022) · Springer eBooks · doi:10.1007/978-3-030-96925-7_10 · Cited by 5
Explainable Machine Learning for Drug Shortage Prediction in a Pandemic Setting
Li, J., Almentero, B. K., & Besse, C. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-25599-1_11 · Cited by 7
Explainable machine learning for hydrocarbon prospect risking
Mustafa, A., Koster, K., & AlRegib, G. (2023) · Geophysics · doi:10.1190/geo2022-0594.1 · Cited by 8
An Ensemble Interpretable Machine Learning Scheme for Securing Data Quality at the Edge
Karanika, A., Oikonomou, P., Kolomvatsos, K., & Anagnostopoulos, C. B. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-57321-8_29 · Cited by 7
“The authors of [40] review explainable machine learning in view of applications in the natural sciences and discuss three core elements i.e., transparency, interpretability, and explainabil-ity.”
BackgroundPredicting Peach Fruit Ripeness Using Explainable Machine Learning
Ljubobratović, D., Guoxiang, Z., Bakarić, M. B., Jemrić, T., & Matetić, M. (2020) · Annals of DAAAM for ... & proceedings of the ... International DAAAM Symposium · doi:10.2507/31st.daaam.proceedings.099 · Cited by 8
“Explanation, according to some authors [12], is a prerequisite to ensure the scientific value of the results.”
BackgroundHybrides Maschinelles Lernen im Kontext der Produktion
Gauger, I., Nagel, T., & Huber, M. F. (2021) · Springer eBooks · doi:10.1007/978-3-662-64408-9_6 · Cited by 5
LOGIC: Probabilistic Machine Learning for Time Series Classification
Berns, F., Hüwel, J. D., & Beecks, C. (2021) · Proceedings · doi:10.1109/icdm51629.2021.00113 · Cited by 5
A Framework for Interactive Visual Interpretation of Remote Sensing Data
Karmakar, C., & Datcu, M. P. (2022) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2022.3161959 · Cited by 6
Explaining Differential Evolution Performance Through Problem Landscape Characteristics
Nikolikj, A., Lang, R. D., Korošec, P., & Eftimov, T. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-21094-5_8 · Cited by 10
Establishing Transparency in Artificial Intelligence Systems
Quakulinski, L., Koumpis, A., & Beyan, O. (2022) · International Conference on Transdisciplinary AI (TransAI) · doi:10.1109/transai54797.2022.00027 · Cited by 6
A Visualization Framework for Unsupervised Analysis of Latent Structures in SAR Image Time Series
Karmakar, C., Dumitru, C. O., Hughes, N., & Datcu, M. P. (2023) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2023.3273122 · Cited by 5
“The end-to-end explainability we mean the following: 1) Each constituent model is intrinsically explainable and computation follow the principles of explainability [6].”
BackgroundMethodInfluentialKharlamova, A., Kruglov, A. V., & Succi, G. (2024) · International Congress on Human-Computer Interaction, Optimization and Robotic Applications (ICHORA) · doi:10.1109/hora61326.2024.10550565 · Cited by 7
“We also need to discuss the reliability of the results generated by machine learning models (a question of reversibility and explainability of a model) [6] [7], as well as potential approaches to addressing these issues in practical applications in the insurance sector.”
BackgroundThe Effect of IoT Data Completeness and Correctness on Explainable Machine Learning Models
Azimi, S., & Pahl, C. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-86475-0_15 · Cited by 7
Interpretable Model-based Hierarchical Reinforcement Learning using Inductive Logic ProgrammingPreprint
Xu, D., & Fekri, F. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.11417 · Cited by 16
“Interpretability There have been a lot of recent papers investigating the interpretability in deep learning [8, 13, 37].”
BackgroundThériault-Lauzier, P., & Chow, B. J. W. (2022) · Canadian Journal of Cardiology · doi:10.1016/j.cjca.2022.02.010 · Cited by 6
Dürauer, A., Jungbauer, A., & Scharl, T. (2023) · doi:10.22541/au.167898784.45653707/v1 · Cited by 5
Das, A., Mishra, M. K., Chakraborty, S., Bhattacharya, B. K., Dave, R. H., Kumar, D., Patel, K. C., Setia, R. K., & Weindorf, D. C. (2025) · European Journal of Soil Science · doi:10.1111/ejss.70161 · Cited by 7
“These AutoML frameworks also provide ways to interpret complex ML models through model-agnostic approaches, which are important for explaining the role of various pedological factors in digital soil modelling (Roscher et al. 2020; Wadoux and McBratney 2021).”
Zhao, Q., Gao, F., He, B., Li, Y., Li, H., Xiao, Y., & Lin, R. (2025) · Agronomy · doi:10.3390/agronomy15081902 · Cited by 4
Küçükakçalı, Z., Çiçek, İ. B., & Akbulut, S. (2025) · Journal of Clinical Medicine · doi:10.3390/jcm14176201 · Cited by 6
“Roscher et al. [21] have discussed how XAI contributes to scientific understanding by clarifying the decision-making processes of ML models.”
Singh, G., Rosman, B., Byrne, M. J., & Reynolds, C. (2025) · Environmental Monitoring and Assessment · doi:10.1007/s10661-025-14517-1 · Cited by 5
“SHAP is preferred and increasingly adopted for model interpretation across various domains (Roscher et al., 2020), including ecology (e.g., Cha et al., 2021; Wang et al., 2021; Yu et al., 2020), because of its theoretical justification (e.g., additivity and consistency properties) and analytical…”
Ren, G., Hou, M., Yang, X., Huang, Y., Li, D., Zhang, N., Liu, P., Ye, H., Chen, Z., & Chen, H. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-02044-9 · Cited by 4
“” They produce discrete, categorical labels — such as ” fi brous ” or ” calci fi ed ”— but offer little in the way of interpretability or contextual understanding 10 .”
Big data analytics in e-learning: ethical challenges and opportunities for engineering education
Dritsas, E., & Τρίγκα, Μ. (2025) · AI and Ethics · doi:10.1007/s43681-025-00866-7 · Cited by 8
“Future research should advance hybrid systems that combine explainable ML with domain-aware logic capable of translating algorithmic inferences into pedagogically grounded actions [107].”
AI for Transmission Electron Microscopy
Li, Y., Ge, M., Liu, X., & Su, D. (2025) · Photon Science · doi:10.1021/photonsci.5c00032 · Cited by 5
Noor, F., & Qamar, M. T. U. (2026) · Briefings in Bioinformatics · doi:10.1093/bib/bbag051 · Cited by 12
“GO, pathways) [129].”
Design Exploration of a Distributed Electric Propulsion Aircraft Using Explainable Surrogate Models
Palar, P. S., Van, E. N., Bartoli, N., & Morlier, J. (2024) · Journal of Aircraft · doi:10.2514/1.c037848 · Cited by 4
Explainable Machine Learning Models for Predicting Recurrence in Differentiated Thyroid Cancer
Arslan, A. K., & Çolak, C. (2024) · Medical Records · doi:10.37990/medr.1525801 · Cited by 4
Wang, P., & Yuan, Y. (2024) · Transactions in GIS · doi:10.1111/tgis.13271 · Cited by 9
“Explainable machine learning refers to a set of techniques and methodologies designed to make the decision-making processes of machine learning models more transparent and under-standable to humans (Roscher et al. 2020).”
Autonome Entdeckung in den chemischen Wissenschaften, Teil II: Ausblick
Coley, C. W., Eyke, N. S., & Jensen, K. F. (2020) · Angewandte Chemie · doi:10.1002/ange.201909989 · Cited by 4
Becker, M., Brockmann, M., Niemietz, P., Trauth, D., Bergs, T., & Brecher, C. (2021) · Springer eBooks · doi:10.1007/978-3-662-62915-4_15 · Cited by 5
Shi, X., Silva, D., Aslan, Y., Ekmekcioǧlu, E., & KONDOZ, A. M. (2021) · Entropy · doi:10.3390/e24010067 · Cited by 5
“model (thus, it is also called post-modelling explainability) processes the information and gives the output [14].”
BackgroundWhat perceptron neural networks are (not) good for?
Calude, C. S., Heidari, S., & Sifakis, J. (2022) · Information Sciences · doi:10.1016/j.ins.2022.11.083 · Cited by 9
Analytical Workflows to Unlock Predictive Power in Biotherapeutic Developability
Trikeriotis, M., Akbulatov, S. V., Esposito, U., Anastasiou, A., & Leszczyszyn, O. I. (2022) · Pharmaceutical Research · doi:10.1007/s11095-022-03448-y · Cited by 5
A research landscape on software defect prediction
Taskeen, A., Khan, S. U. R., & Felix, E. A. (2023) · Journal of Software Evolution and Process · doi:10.1002/smr.2549 · Cited by 7
“97 It is possible yet difficult to explain the findings of the SDP models.”
BackgroundClimate envelope modeling for ocelot conservation planning: peering inside the black box
Lehnen, S. E., & Lombardi, J. V. (2023) · Ecosphere · doi:10.1002/ecs2.4477 · Cited by 6
An Empirical Comparison among Supervised Learning Algorithms with Model Explainability
Tasnim, S. S., Jamal, M. K., Akter, S., Akter, S., & Hossain, S. (2023) · International Conference on Computer and Information Technology (ICCIT) · doi:10.1109/iccit60459.2023.10441508 · Cited by 5
“In this case, Explainability [8] is required to ensure the results of new scientific insights from output [9].”
BackgroundTinyML4D: Scaling Embedded Machine Learning Education in the Developing World
Plancher, B., Büttrich, S., Ellis, J., Goveas, N., Kazimierski, L. D., López, J. A., Lukić, M., Méndez, D., Nordin, R., Trevisan, A. O., et al. (2024) · Proceedings of the AAAI Symposium Series · doi:10.1609/aaaiss.v3i1.31265 · Cited by 10
“…al. 2023), additional work must be done to expand transparency, improve explain-ability, and reduce the bias of real-world embedded ML systems (e.g., by building on recent efforts in large-scale machine learning (Mitchell et al. 2019; Roscher et al. 2020; Mehrabi et al. 2021; Selbst et al. 2019)).”
BackgroundLee, G.-W., Livadiotis, S., & Salamone, S. (2024) · Structural Health Monitoring · doi:10.1177/14759217241260254 · Cited by 5
“38,39 Beyond analyzing model output, this focused approach also serves as a validation for the effectiveness of the proposed features and the concept of waveform uniqueness.”
Explainable Artificial Intelligence for Business and Economics: Methods, Applications and Challenges
Lyu, Q., & Wu, S. (2025) · Expert Systems · doi:10.1111/exsy.70017 · Cited by 10
Yang, Z., Jia, R., Liu, K., He, X., Zhang, X., Wang, S., Zhang, D., Jia, W., Zhang, S., & Zhang, Y. (2025) · Transactions in GIS · doi:10.1111/tgis.70034 · Cited by 4
“…machine learning algorithms also reveals a number of issues, such as sampling instability and variability, machine learning limitations due to dataset complexity, and time and security vulnerabilities in the learning process (Lundberg et al. 2020; Roscher et al. 2020; Ryo et al. 2020).”
Yongcharoenchaiyasit, K., Arwatchananukul, S., Hristov, G., & Temdee, P. (2025) · Bioengineering · doi:10.3390/bioengineering12060592 · Cited by 4
Put it to the Test: Getting Serious About Explanation in Explainable Artificial Intelligence
Boge, F. J., & Mosig, A. (2025) · Minds and Machines · doi:10.1007/s11023-025-09724-1 · Cited by 13
“Following recent developments in XAI (Murdoch et al., 2019; Roscher et al., 2020; Schuhmacher et al., 2022) as well as philosophical accounts of ML’s potential in fostering scientific understanding (Boge, 2022; Räz & Beisbart, 2022; Sullivan, 2022b), we will here argue for two distinct theses—one…”
InfluentialBiryukov, D. N., & Dudkin, A. S. (2025) · Scientific and technical journal of information technologies mechanics and optics · doi:10.17586/2226-1494-2025-25-3-373-386 · Cited by 6
Learning human insight by cooperative AI: Shannon-Neumann measure
Siregar, E. (2021) · IOP SciNotes · doi:10.1088/2633-1357/abec9e · Cited by 4
Applying Explainable Artificial Intelligence Techniques on Linked Open Government Data
Kalampokis, E., Karamanou, A., & Tarabanis, K. A. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-84789-0_18 · Cited by 7
Increasing trust and fairness in machine learning applications within the mortgage industry
van Zetten, W., Ramackers, G. J., & Hoos, H. H. (2022) · Machine Learning with Applications · doi:10.1016/j.mlwa.2022.100406 · Cited by 15
“Roscher et al. (2020) specifically high-light the applications of interpretable machine learning for scientific research, categorising existing scientific research and applications of interpretable ML, covering mostly model-specific examples.”
Multi-stage Bias Mitigation for Individual Fairness in Algorithmic Decisions
Ghadage, A., Yi, D., Coghill, G. M., & Pang, W. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20650-4_4 · Cited by 6
“The researchers have proposed new fundamental pillars for trust in the AI system, including explainability, fairness, robustness, and lineage[4, 26, 3].”
BackgroundBhowmick, S., Nagarajaiah, S., & Kyrillidis, A. (2022) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2022.110059 · Cited by 8
Explainable Representations for Relation Prediction in Knowledge Graphs
Sousa, R. T., Silva, S., & Pesquita, C. (2023) · Principles of Knowledge Representation and Reasoning · doi:10.24963/kr.2023/62 · Cited by 9
Solubilization of inclusion bodies: insights from explainable machine learning approaches
Walther, C., Martinetz, M. C., Friedrich, A., Tscheließnig, A., Voigtmann, M., Jung, A., Brocard, C., Bluhmki, E., & Smiatek, J. (2023) · Frontiers in Chemical Engineering · doi:10.3389/fceng.2023.1227620 · Cited by 4
“…of feature importances with regard to “ explainable machine learning ” approaches (Holzinger et al., 2018; Gunning et al., 2019; Kailkhura et al., 2019; Linardatos et al., 2020; Roscher et al., 2020; Belle and Papantonis, 2021; Burkart and Huber, 2021; Pilania, 2021; Oviedo et al., 2022).”
BackgroundTen propositions on machine learning in official statistics
van Delden, A., Burger, J., & Puts, M. (2023) · AStA Wirtschafts- und Sozialstatistisches Archiv · doi:10.1007/s11943-023-00330-0 · Cited by 5
“Explainability is a broader concept than transparency and interpretability, as it considers the model, the data, and human involvement (Roscher et al. 2020).”
Huynh, T.-H., & Yoo, M. (2020) · Applied Sciences · doi:10.3390/app10196800 · Cited by 5
Knowledge-based XAI through CBR: There is more to explanations than models can tellPreprint
Weber, R. O., Shrestha, M., & Johs, A. J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.10363 · Cited by 8
Betancourt, C., Stomberg, T. T., Edrich, A.-K., Patnala, A., Schultz, M. G., Roscher, R., Kowalski, J., & Stadtler, S. (2022) · doi:10.5194/gmd-2022-2 · Cited by 4
Self-citationExplaining Explainability: Interpretable machine learning for the behavioral sciencesPreprint
Kennedy, B., Reimer, N. K., & Dehghani, M. (2021) · PsyArXiv (OSF Preprints) · doi:10.31234/osf.io/9h6qr · Cited by 5
Kolmogorov-Arnold Networks for Data-Driven Turbulence Modeling
Alhafiz, M. R., Zakaria, K., Dung, D. V., Palar, P. S., Dwianto, Y. B., & Zuhal, L. R. (2025) · AIAA SciTech Forum · doi:10.2514/6.2025-2047 · Cited by 3
Experimental study on automation and data-driven modeling in the punching-collar forming process
Korenek, J., Riemer, M., Kräusel, V., Langhammer, D., & Koschmider, A. (2025) · at - Automatisierungstechnik · doi:10.1515/auto-2024-0104 · Cited by 3
“In addition, Explanable AI (XAI) brings the next step of transparency, interpretability and explainability of model outputs by incorporating experience and expert knowledge [1].”
Can AI Be Useful in the Early Detection of Pancreatic Cancer in Patients with New-Onset Diabetes?
Mejza, M., Bajer, A., Wanibuchi, S., & Małecka-Wojciesko, E. (2025) · Biomedicines · doi:10.3390/biomedicines13040836 · Cited by 3
“It can also be an excellent tool for better understanding casual relationships from non-randomized data sets [46].”
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.