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 601–700 of 999
Rosa, R. C., Gonçalves, M. C., & Barbalho, S. C. M. (2025) · International Journal of Production Economics · doi:10.1016/j.ijpe.2025.109688 · Cited by 3
Infrared Spectra‐Based Machine Learning Framework for Photocatalytic Reaction and Performance
Wang, Y., Sun, Y., Wang, H., Li, J., Liu, X., & Dong, F. (2025) · Advanced Intelligent Systems · doi:10.1002/aisy.202500101 · Cited by 4
Soil Moisture Prediction Using Artificial Neural Networks and Remote Sensing Data
Singh, A., Kumar, A., Singh, A., Tiwari, R. K., Chaurasiya, N., Singh, A., Singh, S. S., & Singh, M. P. (2025) · Remote Sensing in Earth Systems Sciences · doi:10.1007/s41976-025-00240-5 · Cited by 3
“ANNs, grounded in an understanding of Earth’s processes, leverage explainable machine learning to provide predictions rooted in the real world [14–16].”
Hisam, E., Sertel, E., & Şeker, D. Z. (2025) · The Science of The Total Environment · doi:10.1016/j.scitotenv.2025.180540 · Cited by 4
Zhu, J., Zhou, Q., Chen, L., He, Z., Tan, J., Pang, J., & Ni, Q. (2025) · BMC Cancer · doi:10.1186/s12885-025-14999-9 · Cited by 6
“Interpretability is crucial for extracting genuinely novel scientific insights and ideas from machine learning meth-ods [26].”
Empowering scientific discovery with explainable small domain-specific and large language models
Yu, H., Wang, Y., Cheng, T., Yan, Y., Dawson, K. A., Li, S. F. Y., Zheng, Y., & Jin, Y. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11365-w · Cited by 5
“Some surveys and reviews, based on the above concepts, introduced the XAI into scientific community (Roscher et al. 2020 ) and specific fields, especially for the fields of materials and chemistry (Feng et al. 2020 ; Oviedo et al. 2022 ), medicine and healthcare (Tjoa and Guan 2021 ; Klauschen et…”
AI and Human Resources: Ethical Concerns and Potential Spots of Biases
Jalan, S., & Jena, L. K. (2025) · Emerald Group Publishing Limited eBooks · doi:10.1108/978-1-83662-982-520251003 · Cited by 3
Ariouat, H., Pimparé, E. P., Chenin, E., Pignal, M., Vignes‐Lebbe, R., Arib, S., Prifti, E., Zucker, J., & Sklab, Y. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.09.499 · Cited by 3
Kumar, M., Wu, R.-Z., Yeh, S., Wu, E. H., & Tsai, P. (2025) · IEEE Journal of Translational Engineering in Health and Medicine · doi:10.1109/jtehm.2025.3638643 · Cited by 3
“Meanwhile, advances in big data and AI have enabled machine learning to uncover patterns in behavioral and linguistic data for accurate classification, progress tracking, and outcome prediction [14].”
Discovering interpretable blast Loading equations from Black-Box Machine learning models
Shi, Z., Li, Q., Shao, Y., Li, L., & Hao, H. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.104244 · Cited by 5
Verrelst, J., Clerck, E. D., Verma, B., Mishra, K., & Caballero, G. R. (2026) · Remote Sensing · doi:10.3390/rs18081154 · Cited by 4
Review of Progress of AI in Biomimetics: From Biological Patterns to Closed-Loop Discovery
Hu, Z., Hong, H., & Lin, T. (2026) · Biomimetics · doi:10.3390/biomimetics11050320 · Cited by 5
“In safety-critical fields, such as aerospace and tissue engineering, understanding the rationale behind an AI recommendation is as crucial as its performance [206].”
Padmanabhan, K., Lu, M., Feng, D., Kan‐Dobrosky, N., Konduri, S., Litman, H. J., & Livieratos, A. (2026) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocag077 · Cited by 4
“XML covers three related concepts: transparency, interpretability, and explainability [10] .”
Zahmatkesh, A., & Lung, C. (2022) · Lecture notes in computer science · doi:10.1007/978-3-030-98978-1_9 · Cited by 3
Mai, L., Köchling, A., & Wehner, M. (2022) · SN Computer Science · doi:10.1007/s42979-022-01137-6 · Cited by 4
“Although one might assume higher objectivity in assessing and evaluating learning outcomes by a computer system rather than a human, the literature discussed the problems of potential biases and discrimination of machine learning systems [39].”
BackgroundAviyente, S., & Karaaslanli, A. (2022) · IEEE Signal Processing Magazine · doi:10.1109/msp.2022.3149471 · Cited by 3
On Explainability in AI-Solutions: A Cross-Domain Survey
Antón, S. D. D., Schneider, D., & Schotten, H. D. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-14862-0_17 · Cited by 6
“Roscher et al. present an overview of methods to conserve scientific interpretability and explainability in natural sciences [53].”
Mao, Y., Duan, Y., Guo, Y., Wang, X., & Gao, S. (2022) · Journal of Mathematics · doi:10.1155/2022/2068353 · Cited by 5
“As machine learning develops rapidly, models can achieve high levels of prediction accuracy, and the need for interpretable machine learning is also growing to ensure the reasons why models make decisions are reliable, which is essential for using machine learning to find truly novel scientific results [58].”
BackgroundTransparency in Medical Artificial Intelligence Systems
Quakulinski, L., Koumpis, A., & Beyan, O. (2023) · International Journal of Semantic Computing · doi:10.1142/s1793351x23630011 · Cited by 3
A coupled model applied to complex river–lake systems
Zhang, Q., Zhan, C., Wang, Y., Zhang, H., & Lin, Z. (2023) · Hydrological Sciences Journal · doi:10.1080/02626667.2023.2285441 · Cited by 4
“2013, Roscher et al .”
Mesh-Agnostic Decoders for Supercritical Airfoil Prediction and Inverse Design
Li, R., Zhang, Y., & Chen, H. (2024) · AIAA Journal · doi:10.2514/1.j063387 · Cited by 3
“Interpretability usually means making sense of the obtained model or results [4].”
BackgroundPlaen, J. J.-F. G. D., Koks, E., & Ward, P. J. (2024) · Environmental Research Infrastructure and Sustainability · doi:10.1088/2634-4505/ad63c9 · Cited by 8
“These concerns, dating back to the 1990s, are progressively being adopted in both the remote sensing community (Roscher et al 2020, Gevaert 2022) and disaster risk management (Wagenaar et al 2020, Moitra et al 2022).”
Perception-based constraint solving for sudoku images
Mulamba, M., Mandi, J., Mahmutoğulları, A. İ., & Guns, T. (2024) · Constraints · doi:10.1007/s10601-024-09372-9 · Cited by 10
“Another important aspect of neuro-symbolic reasoning is that the explicit modeling of knowledge provides interpretability, leading towards explainable AI [11].”
BackgroundCan We Trust the Machine Learning Based Geotechnical Model?
Hansen, T. F. (2024) · Springer series in geomechanics and geoengineering · doi:10.1007/978-3-031-76528-5_33 · Cited by 4
Bockel-Rickermann, C., Verboven, S., Verdonck, T., & Verbeke, W. (2024) · Decision Support Systems · doi:10.1016/j.dss.2024.114378 · Cited by 12
Maita, A. R. C., Fantinato, M., Peres, S. M., & Maggi, F. M. (2025) · Künstliche Intell. · doi:10.1007/s13218-024-00878-1 · Cited by 3
“Interpreting predictive models is essential for creating trust-worthy, transparent, and accountable ML-based systems that align with ethical standards and foster user trust and understanding [17, 42, 43].”
Daghigh, V., Daghigh, H., & Keller, M. W. (2025) · Journal of Composites Science · doi:10.3390/jcs9030100 · Cited by 3
Liu, Y., Liu, Y., Zhang, S., Zeng, C., Zhang, Q., Jiang, Y., Yang, X., Zhang, Q., Ge, Q., Jiang, Y., et al. (2025) · Toxicology Letters · doi:10.1016/j.toxlet.2025.03.008 · Cited by 3
An evolutionary approach to interpretable learning
Robertson, J., & Hu, T. (2021) · Genetic and Evolutionary Computation Conference Companion (GECCO Companion) · doi:10.1145/3449726.3459460 · Cited by 3
A Whale’s Tail - Finding the Right Whale in an Uncertain World
Marcos, D., Kierdorf, J., Cheeseman, T., Tuia, D., & Roscher, R. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-04083-2_15 · Cited by 5
Self-citationSolving problems of the oil and gas sector using machine learning algorithms
(2021) · Acta Montanistica Slovaca · doi:10.46544/ams.v26i2.11 · Cited by 4
“Recently machine learning algorithms began to spread to all areas of the industry, and the oil&gas sector was not an exception (Meng et al., 2020; Roscher et al., 2020; Goodfellow et al., 2016).”
BackgroundThe Mirror Agent Model: A Bayesian Architecture for Interpretable Agent Behavior
Persiani, M., & Hellström, T. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-15565-9_7 · Cited by 5
“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 [18].”
BackgroundSeo, S. B., & Cho, H.-K. (2022) · Frontiers in Medicine · doi:10.3389/fmed.2022.1037647 · Cited by 3
“The XAI algorithm aims for three things: transparency, interpretability, and explanation (34).”
MethodPhase space approach to solving higher order differential equations with artificial neural networks
Tori, F., & Ginis, V. (2022) · Physical Review Research · doi:10.1103/physrevresearch.4.043090 · Cited by 3
Becker, M., Brockmann, M., Niemietz, P., Trauth, D., Bergs, T., & Brecher, C. (2023) · Springer eBooks · doi:10.1007/978-3-662-66509-1_15 · Cited by 3
Optimized reaction coordinates for analysis of enhanced sampling
Widmer, J., Langini, C., Vitalis, A., & Caflisch, A. (2023) · The Journal of Chemical Physics · doi:10.1063/5.0149207 · Cited by 4
Akiyama, K., & Ogawa, H. (2023) · TRANSACTIONS OF THE JAPAN SOCIETY FOR AERONAUTICAL AND SPACE SCIENCES · doi:10.2322/tjsass.66.164 · Cited by 4
An Interpretation Study on the ML Models for Landslide Susceptibility Mapping
Lv, L., Chen, T., & Li, J. (2023) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss52108.2023.10282171 · Cited by 3
“Therefore, explainable artificial intelligence (XAI) technology has attracted much attention as a powerful interpretation tool, which can comprehensively explain the output results of complex ML algorithms [4].”
BackgroundExplainability of Artificial Intelligence Systems: A Survey
Hossain, M., Das, S., Krishnamurthy, B., & Shiva, S. G. (2023) · International Symposium on Networks, Computers and Communications (ISNCC) · doi:10.1109/isncc58260.2023.10323642 · Cited by 4
“Roscher et al. [14] surveyed recent scientific works, combined domain knowledge with explainable machine learning, and contrasted transparency, interpretability, and explainability.”
BackgroundThe Role and Challenges of Machine Learning in the Construction of a Community of Human Destiny
Zhang, Z. (2024) · Journal of Electrical Systems · doi:10.52783/jes.1614 · Cited by 4
“Additionally, the interpretability of ML models is a critical issue, as the decision-making processes of complex models are often opaque, making it difficult to understand and trust their predictions [15].”
BackgroundAccelerating aerodynamic simulations with a hybrid fine-tuned deep learning model
Li, J., Zhang, X.-Y., Peng, W., Liu, X., Wang, W., & Yao, W. (2024) · Physics of Fluids · doi:10.1063/5.0238746 · Cited by 3
The uropathologist of the future: getting ready with intelligence for the prostate cancer tsunami
Cimadamore, A., Montironi, R., Liang Cheng, C., Antonio Lopez-beltran, B., Rogers, E. T., Franzese, C., Crestani, A., & Giannarini, G. (2024) · Pathologica · doi:10.32074/1591-951x-1047 · Cited by 3
Muttaqin, R., & Sudiana, D. (2025) · Jurnal Penelitian Pendidikan IPA · doi:10.29303/jppipa.v10i12.8346 · Cited by 9
Eris, O., Bozkurt, M. R., Eris, S. B., & Bílgín, C. (2025) · IEEE Access · doi:10.1109/access.2025.3546720 · Cited by 4
“We preferred these algorithms because of their fast operation, applicability to embedded systems, not requiring computers with high processing capacity, and high-performance classification [23], [25], [26], [33], [65], [66], [67], [68].”
Multi-exit Kolmogorov–Arnold networks: enhancing accuracy and parsimony
Bagrow, J. P., & Bongard, J. (2025) · Machine Learning Science and Technology · doi:10.1088/2632-2153/adf9bd · Cited by 10
“This accuracy–interpretability trade-off remains a critical bottleneck for the adoption of machine learning in scientific discovery, where understanding the underlying relationships is often as important as making accurate predictions [2, 4].”
InfluentialAbbasi, J., & Andersen, P. Ø. (2022) · EAGE Conference and Exhibition incorporating SPE EUROPEC · doi:10.2118/209667-ms · Cited by 5
Automatic Botnet Attack Identification Based on Machine Learning
Li, P. H., Xu, J., Xu, Z. Y., Chen, S., Niu, B. W., Yin, J., Sun, X. F., Lan, H. L., & Chen, L. L. (2022) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2022.029969 · Cited by 4
Exploring Root Causes of CNN-Based Image Classifier Failures Using 3-Nearest Neighbors
Bilgin, Z., & Güneştaş, M. (2022) · SN Computer Science · doi:10.1007/s42979-022-01360-1 · Cited by 3
“The work [31] examines XAI from the perspective of applications in the natural sciences and discusses three main relevant concepts of transparency, interpretability, and explainability.”
BackgroundOvalle, C. (2022) · International Conference on Computers in Management and Business (ICCMB) · doi:10.1145/3512676.3512713 · Cited by 3
“On the other hand, a Machine Learning approach is transparent "if the processes that extract the parameters from the training data model generate labels from the test data, these can be described and motivated by the focus designer" [13]; then, that transparency depends on the general structure of themodel, the indivi…”
BackgroundHaghighatlari, M., Li, J., Heidar‐Zadeh, F., Liu, Y., Guan, X., & Head-Gordon, T. L. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.00157 · Cited by 3
Spline parameterization of neural network controls for deep learningPreprint
Günther, S., Pazner, W., & Qi, D. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.00301 · Cited by 3
“…practical applications of deep learning, including classical machine learning areas such as image recognition, classification or segmentation [12, 22] or natural language processing [8], as well as applications in the new and rapidly evolving field of scientific machine learning [20, 14, 13, 24, 23].”
BackgroundToward Building Science Discovery MachinesPreprint
Khalili, A., & Bouchachia, A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.15551 · Cited by 5
“[87] provided a survey of recent applications of machine learning in scientific discovery and the way that explainable machine learning is used in combination with domain knowledge from the application areas.”
BackgroundArtificial General Intelligence: A New Perspective, with Application to Scientific DiscoveryPreprint
Khalili, A. M. (2022) · Engineering Archive (engrXiv) · doi:10.31224/osf.io/duz8g · Cited by 6
“The landscape of AGI is extremely vast, in this paper we will focus on the scientific discovery process [6-8, 33-37, 41-42, 54-55, 77, 81, 85, 87-91, 116-123, 149]. problems, this approach has key limitations in its generalization ability as discussed in earlier sections.”
BackgroundSub-setting algorithm for training data selection in pattern recognition
Arwade, G. (2021) · doi:10.31274/td-20240329-704 · Cited by 3
Васильевич, С. В., Proletarsky, A. V., Александрович, М. Д., & Игоревич, Д. И. (2024) · International Youth Conference on Radio Electronics, Electrical and Power Engineering (REEPE) · doi:10.1109/reepe60449.2024.10479674 · Cited by 2
“The article [28] relates the extreme importance of the interpretability of the artificial intelligence results and machine learning in the field of science: explainability is a necessary condition for ensuring the scientific value of the result, since in natural sciences, the main goals of using…”
BackgroundOlaya, J. F. C., & Corrales, J. C. (2024) · Frontiers in Sustainable Food Systems · doi:10.3389/fsufs.2024.1363744 · Cited by 2
Human Movement Recognition with Machine Learning Techniques
Sinha, R. K., Sinha, P. C., & Tiwari, M. (2024) · IEEE International Conference on Advances in Computing Research on Science Engineering and Technology (ACROSET) · doi:10.1109/acroset62108.2024.10743652 · Cited by 2
dos Santos, J. D. M., Reis, L. P., & dos Santos, J. P. M. (2025) · Machine Learning and Knowledge Extraction · doi:10.3390/make7010017 · Cited by 3
“Here, xAI methods are applied to make the ANN’s operations transparent and interpretable, allowing for knowledge extraction from data in a typical cognitive task [22].”
The value of real-time automated explanations in stochastic planning
Goldman, C. V., Bustin, R., Qi, W., Xing, Z., McPhearson-White, R., & Rogers, S. J. (2025) · Artificial Intelligence · doi:10.1016/j.artint.2025.104323 · Cited by 4
Zhang, W., Qu, R., Fang, Z., Gao, C., Fang, Z., Wen, C., Guan, X., Sun, W. M., & He, J. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3568392 · Cited by 4
Transfer Learning for Distance Classification of Marine Vessels Using Underwater Sound
Wout, D., Deneudt, K., Parcerisas, C., Schall, E., & Debusschere, E. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3593779 · Cited by 5
“In contrast, machine learning techniques, such as convolutional neural networks (CNNs), offer a promising alternative by providing faster, more flexible, and more efficient solutions [19], [35], [36], [37], [46].”
Deploying Virtual Quality Gates in a Pilot-Scale Lithium-Ion Battery Assembly Line
Xu, X., Stier, S., Gronbach, A., & Moeckel, M. (2025) · Batteries · doi:10.3390/batteries11080285 · Cited by 3
Advancing research software engineering with AI: a research framework
Farshidi, S., Bennin, K. E., Babur, Ö., Sallou, J., Kassahun, A., & Tekinerdoğan, B. (2026) · Automated Software Engineering · doi:10.1007/s10515-026-00621-0 · Cited by 9
“Studies on AI code generation, explainability, and machine learning engineering typically address generic or industrial software systems (Odeh 2024; Ali et al. 2023; Roscher et al. 2020; Allamanis et al. 2018).”
A complex system approach to magmatism
Annen, C., Weinberg, R. F., Moyen, J., & Cazabet, R. (2025) · Nature Reviews Earth & Environment · doi:10.1038/s43017-025-00697-4 · Cited by 2
“Advanced machine learning is widely used in many scientific domains 132 , including medicine, astrophysics, biology and social sciences to explore the mechanisms of complex systems 133,134 .”
Dataism, skepticism, and intuition for interpretable machine learning
Naser, M. Z. (2025) · AI and Ethics · doi:10.1007/s43681-025-00831-4 · Cited by 2
“Furthermore, prior work has examined ethical and social facets of algorithms but has rarely engaged directly with the interplay between ML enthusiasm, skeptical rigor, and the intuitive dimension of engineering [16].”
Machine learning method for wall thermal resistance evaluation in hot summer and warm winter regions
Zhang, L., Li, J., & Zhang, Y. (2025) · Journal of Building Engineering · doi:10.1016/j.jobe.2025.113956 · Cited by 1
Revealing drivers of green technology adoption through explainable Artificial Intelligence
Kistinger, D., Titz, M., Böttcher, P., Schaub, M. T., Venghaus, S., & Witthaut, D. (2025) · Advances in Applied Energy · doi:10.1016/j.adapen.2025.100242 · Cited by 3
Islam, M. R., Weber, R. O., Ahmed, M. U., & Begum, S. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.114599 · Cited by 4
Tuning hyperparameters and improving models
Maxwell, A. E., Ramezan, C. A., & He, Y. (2025) · Elsevier eBooks · doi:10.1016/b978-0-443-29306-1.00008-9 · Cited by 2
Iqbal, N., Shabbir, K., & Noureldin, M. (2025) · Machine Learning with Applications · doi:10.1016/j.mlwa.2025.100760 · Cited by 2
Sarkar, S., Young, B. A., Daniels, C. S., & Thompson, J. E. (2025) · Journal of Dairy Science · doi:10.3168/jds.2025-27394 · Cited by 2
A new parametric information-gain criterion for tree-based machine learning algorithms
Costa, D., Costa, V. V., & Rocha, E. (2025) · PeerJ Computer Science · doi:10.7717/peerj-cs.3319 · Cited by 4
Interpretable feature interaction via statistical self-supervised learning on tabular data
Zhang, X., & Xiong, H. (2025) · Machine Learning Science and Technology · doi:10.1088/2632-2153/ae3104 · Cited by 3
“Scientific datasets are often high-dimensional, noisy, and governed by theoretical constraints, making explainable AI (XAI) for science essential [1].”
Shi, X., Lyu, W., Ding, W., Wang, Y., Yang, Y., & Wang, L. (2026) · Sustainability · doi:10.3390/su18020820 · Cited by 4
Chinilin, A. V., Лозбенев, Н. И., Shilov, P. M., Fil, P. P., Khitrov, N. B., & Козлов, Д. Н. (2026) · Eurasian Soil Science · doi:10.1134/s1064229325602604 · Cited by 2
“Despite their predictive possibilities, most of advanced machine learning models used in soil science are usually considered to be “black boxes,” lacking transparency in the logics they are based on and attribution of features [27, 44] (Table 1).”
Rahmouni, B., Aouadj, M., Mouss, D., Belounis, A. M., & Berghout, T. (2026) · Multimedia Tools and Applications · doi:10.1007/s11042-026-21374-8 · Cited by 3
“Interpretability, involves understanding the model’s structure and how features influence predictions before making them (i.e., pre-prediction), often seen in simpler models like linear regression [ 20 , 21].”
Adenutsi, C. D., Hayford, K., Abdul-Mumin, T., Sarkodie, K., & Erzuah, S. (2026) · Petroleum Science and Technology · doi:10.1080/10916466.2026.2642141 · Cited by 2
Orman, R. Ç. (2026) · Energies · doi:10.3390/en19071603 · Cited by 2
Interpreting black-box machine learning based species distribution models
Cherif, Y., & Idri, A. (2026) · Ecological Complexity · doi:10.1016/j.ecocom.2026.101158 · Cited by 2
Explainable Artificial Intelligence Through the Lens of Bibliometric Citation Analysis
Russo, M., & Vistocco, D. (2026) · Applied Stochastic Models in Business and Industry · doi:10.1002/asmb.70091 · Cited by 2
Tang, J., Cao, L., Xu, G., & Li, M. (2026) · ACS Applied Materials & Interfaces · doi:10.1021/acsami.6c05353 · Cited by 3
Explainable artificial intelligence in finance: A bibliometric review
Ammar, O. H., Rejeb, A., & Rejeb, K. (2026) · Finance Research Open · doi:10.1016/j.finr.2026.100131 · Cited by 4
Shang, G., Wang, X., Li, Y. X., Zhang, Z., Lv, J., & He, W. (2026) · Ecological Indicators · doi:10.1016/j.ecolind.2026.115130 · Cited by 2
Polverino, S., Ahmadnia, H., Rahbarianyazd, R., Mobaraki, A., & Mobaraki, B. (2026) · Remote Sensing · doi:10.3390/rs18142325 · Cited by 2
Głuchowska, A., Khan, M. H. U., & Pawełkowicz, M. E. (2026) · Applied Sciences · doi:10.3390/app16147275 · Cited by 4
VtNet: A neural network with variable importance assessment
Zhang, L., Lin, L., & Li, J. (2020) · Stat · doi:10.1002/sta4.325 · Cited by 2
“See Roscher et al. (2020) for a survey on explainable machine learning.”
BackgroundWindow Size Optimization for Gaussian Processes in Large Time Series Forecasting
Gómez-González, J. L., & Cárdenas‐Montes, M. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-86271-8_12 · Cited by 2
Deep Learning Applied to Scientific Discovery: A Hot Interface with Philosophy of Science
Vervoort, L., Shevlin, H., Melnikov, A. A., & Alodjants, A. P. (2023) · Journal for General Philosophy of Science · doi:10.1007/s10838-022-09625-2 · Cited by 5
“…done by scientists, such as solving quantum many-body problems (Carleo and Troyer 2017 ), discovery of latent properties (Zheng et al. 2018 ), generation of quantum experiments (Melnikov et al. 2018 ), and many more (review texts are, for instance, Dunjko and Briegel 2017 ; Roscher et al. 2020 ).”
BackgroundA computational social science approach to understanding predictors of Chafee service receipt
Yan, J., Hall, S. F., Sage, M., Du, Y., & Joseph, K. (2024) · Children and Youth Services Review · doi:10.1016/j.childyouth.2024.107454 · Cited by 6
Chen, Y., Wu, C., & Chen, W. (2023) · Atmospheric Science Letters · doi:10.1002/asl.1150 · Cited by 2
“In addition, it is desirable that the model can provide three core elements, namely, transparency, interpretability, and explainability (Roscher et al., 2020).”
BackgroundClinical Neuroinnovation: Ethical Frameworks and Emerging Issues
Kasun, M., Dunn, L. B., Palmer, B. W., Kim, J. P., & Roberts, L. W. (2023) · Springer eBooks · doi:10.1007/978-3-031-14339-7_3 · Cited by 2
Guan, Z., Zhang, P., Gu, H., Lu, T., Liu, B., & Gu, N. (2023) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2023.3281674 · Cited by 3
“The framework has been widely used in different interpretation scenarios like philosophical concept explanation [9], mathematics notion explanation [10], and explainable AI [8], [11], [12].”
MethodLi, M., & Lin, Z. (2023) · International Conference on Intelligent Computing and Human-Computer Interaction (ICHCI) · doi:10.1109/ichci58871.2023.10277714 · Cited by 2
“The potential of IML in investigating and discovering underlying patterns in educational data was highlighted [3].”
BackgroundSelecting Top-k Data Science Models by Example Dataset
Wang, M., Guan, S. U., Ma, H., Bian, Y., Che, H., Daundkar, A., Sehirlioglu, A., & Wu, Y. (2023) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3583780.3615051 · Cited by 6
“Moreover, valuable auxiliary metadata should also be suggested (such as training setup, hyper-parameter settings, experimental parameters, and data providers) to help the querier validate the suggested models [19].”
BackgroundQuantitative Explainable AI For Face Recognition
Peng, S., Dong, N., & Bai, G. (2023) · IEEE International Conference on Engineering of Complex Computer Systems (ICECCS) · doi:10.1109/iceccs59891.2023.00014 · Cited by 2
“Explainable AI (XAI) is artificial intelligence that can improve the transparency and interpretability of an AI model, meaning that how easy that the expert can describe the model structure, model components, algorithms, and the reason for specific results from the AI model [18].”
BackgroundMolladavoudi, S., & Yung, W. (2023) · AStA Wirtschafts- und Sozialstatistisches Archiv · doi:10.1007/s11943-023-00331-z · Cited by 4
“Thethird aspect considered by Roscher et al. (2020) is explainability.”
InfluentialPalar, P. S., & Renganathan, S. A. (2024) · AIAA SciTech Forum · doi:10.2514/6.2024-0789 · Cited by 2
Novel Insights into the Antimicrobial Resistance and Strategies to Curb the Menace
Panda, B., Rath, P. K., Mishra, B. P., Mishra, J., Jena, B., Mishra, P. S., Chakraborty, A., Hota, D., & Jena, M. K. (2024) · Journal of Pure and Applied Microbiology · doi:10.22207/jpam.18.1.42 · Cited by 2
DIGITAL TRANSFORMATION IN INDUSTRY 4.0: A BIBLIOMETRIC ANALYSIS
Sopi, J. M., & Hanafi, M. H. (2024) · International Journal of Innovation and Industrial Revolution · doi:10.35631/ijirev.616002 · Cited by 2
Ahmad, M., Ali, M. A., Hasan, M. R., Mobo, F. D., & Rai, S. I. (2024) · Advances in geospatial technologies book series · doi:10.4018/979-8-3693-6381-2.ch010 · Cited by 10
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.