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 701–800 of 999
Supporting Interpretability in Predictive Process Monitoring Using Process Maps
Maita, A. R. C., Fantinato, M., Peres, S. M., & Maggi, F. M. (2024) · Lecture notes in business information processing · doi:10.1007/978-3-031-64748-2_11 · Cited by 3
Generating in-store customer journeys from scratch with GPT architectures
Horikomi, T., & Mizuno, T. (2024) · The European Physical Journal B · doi:10.1140/epjb/s10051-024-00778-1 · Cited by 4
“Like in other scientific realms [10], this shift from hypothesis-driven to data-driven machine learning for discovering important points is the key contribution of this paper.”
X-OODM: Explainable Object-Oriented Design Methodology
Javed, A., Shoaib, M., & Jaleel, A. (2024) · IEEE Access · doi:10.1109/access.2024.3477553 · Cited by 3
“Therefore, explainable systems enhance the accountability of the system and incorporate compliance with regulatory standards [12], which is important in various domains including healthcare, finance, and education [13].”
BackgroundBehavioral Analysis of Android Riskware Families Using Clustering and Explainable Machine Learning
Alani, M. M., & Alawida, M. (2024) · Big Data and Cognitive Computing · doi:10.3390/bdcc8120171 · Cited by 2
Explainable AI in Manufacturing
Zeiser, T., Ehret, D., Lutz, T., & Saar, J. (2024) · IEEE International Conference on Engineering, Technology and Innovation (ICE/ITMC) · doi:10.1109/ice/itmc61926.2024.10794363 · Cited by 6
“To date, there is no standardised definition for explainable AI systems [13], [14].”
Research on intelligent endpoint determination in copper converting based on machine learning
Zhao, B., Hao, H., Xu, J., Chen, E., Lu, Y., & Wang, H. (2025) · Canadian Metallurgical Quarterly · doi:10.1080/00084433.2025.2471617 · Cited by 2
Role and Use of Race in Artificial Intelligence and Machine Learning Models Related to Health
Were, M. C., Li, A., Malin, B., Yin, Z., Coco, J., Collins, B. X., Clayton, E. W., Novak, L. L., Hendricks‐Sturrup, R., Oluyomi, A., et al. (2025) · Journal of Medical Internet Research · doi:10.2196/73996 · Cited by 5
“Efforts to improve explainability of AI [88-90] can support decision-making on which AI and ML models an organization should deploy [91,92].”
Knowledge-inspired fusion strategies for the inference of PM 2.5 values with a neural network
Dabrowski, M., Mennesson, J., Riedi, J. C., Djéraba, C., & Nabat, P. (2025) · Geoscientific model development · doi:10.5194/gmd-18-3707-2025 · Cited by 2
“…in applications fields like finance, medicine, law and even scientific production (Beckh et al., 2021; Murdoch et al., 2019; Belle and Papantonis, 2021; Roscher et al., 2020). those fields, the ability to explain a model and its results can represent the ability to ensure safety, fairness or…”
Salazar, E., Salas, P., & Sáez, P. (2025) · Quality & Quantity · doi:10.1007/s11135-025-02275-8 · Cited by 2
“In this context, explainable AI (XAI) have emerged as powerful tools for interpreting complex ML models, helping analysts uncover how individual attributes contribute to model predictions (Roscher et al. 2020; Zhou et al. 2023).”
Алгоритм коррекции метода биграмм в задаче идентификации автора текста
Voronina, M. Y., Voronina, M. Y., Кислицын, А. А., Орлов, Ю. Н., & Orlov, Y. N. (2022) · Matematicheskoe modelirovanie · doi:10.20948/mm-2022-09-01 · Cited by 2
On the conditions for integrating deep learning into the study of visual politics
Magnani, M., & Segerberg, A. (2021) · ACM Web Science Conference (WebSci) · doi:10.1145/3447535.3462511 · Cited by 3
“The literature observes that a certain transparency can be achieved by communicating and motivating the processes involved, that is how we extracted the model parameters from the training data and how we generated the labels [43].”
BackgroundNovel time slicing approach for customer defection models in e-commerce: a case study
Georgiou, K., & Chasapis, A. (2022) · Data Science and Management · doi:10.1016/j.dsm.2022.07.001 · Cited by 6
A Deep Learning-Based Methodology for Detecting and Visualizing Continuous Gravitational Waves
Pintelas, E. G., Livieris, I. E., & Pintelas, P. (2023) · IFIP advances in information and communication technology · doi:10.1007/978-3-031-34111-3_1 · Cited by 2
Grau‐Luque, E., Becerril‐Romero, I., Pérez-Rodríguez, A., Guc, M., & Izquierdo‐Roca, V. (2023) · The Journal of Open Source Software · doi:10.21105/joss.05873 · Cited by 2
Synergizing AI and Physical Expertise to Close the Water Budget from Satellite Data
Aires, F., & Pellet, V. (2024) · Journal of Hydrometeorology · doi:10.1175/jhm-d-23-0001.1 · Cited by 2
Lopez-Radcenco, M., Delouis, J. ‐., & Vibert, L. (2021) · Astronomy and Astrophysics · doi:10.1051/0004-6361/202040152 · Cited by 6
Xu, H., Sang, S., Yao, H., Herghelegiu, A. I., Lu, H., Yurkovich, J. T., & Yang, L. (2021) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2021.07.02.450937 · Cited by 4
Bhowmick, S., & Nagarajaiah, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.07471 · Cited by 2
“…shortcomings by proposing the method of SNAPE ( S imulta N eous Basis Function A pproximation and P arameter E stimation) which stands on the ideals of theory-guided learning [Karpatne et al., 2017, Roscher et al., 2020], a progressive practice of data science in the scientific community.”
MethodA Comprehensive Review of Machine Learning Techniques for Smart Grid Optimization
Gupta, G., Tomar, A., Pamulaparthyvenkata, S., & Balakrishnan, A. (2025) · Wiley eBooks · doi:10.1002/9781394271849.ch2 · Cited by 6
Ari, M., Emsen, B., Doğan, M., & Şarlar, K. (2025) · Research Square · doi:10.21203/rs.3.rs-7511345/v1 · Cited by 2
When is gray-box modeling advantageous for virtual flow metering?
Hotvedt, M., Grimstad, B., Ljungquist, D., & Imsland, L. (2022) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2022.07.496 · Cited by 2
Data-Driven Suitability Analysis to Enable Machine Learning Explainability and Security
Wolf, S., Foster, R., Haile, J., & Borowczak, M. (2021) · Resilience Week (RWS) · doi:10.1109/rws52686.2021.9611792 · Cited by 1
Tiwari, R. G., Maheshwari, H., Srivastava, V., Srivastava, M., & Agarwal, A. K. (2023) · International Conference on Technological Advancements in Computational Sciences (ICTACS) · doi:10.1109/ictacs59847.2023.10389859 · Cited by 1
“When applied to the task of categorizing visitors’ spending in Tanzania, XML can provide light on the many aspects that impact tourists’ discretionary income [5], [6].”
BackgroundPolynomial-Based Shapley Additive Explanations for Design Exploration in Turbomachinery
Palar, P. S., Shimoyama, K., & Obayashi, S. (2024) · AIAA SciTech Forum · doi:10.2514/6.2024-1226 · Cited by 1
Achieving Equalized Explainability Through Data Reconstruction
Wang, S., & Wu, Y. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10651184 · Cited by 5
“This opacity has sparked an increasing demand for better explain-ability in machine learning, highlighting the need for a deeper understanding of how these models work and make decisions [1]–[3].”
BackgroundOptimized Martian Dust Displacement Detection Using Explainable Machine Learning
Lomashvili, A., Rammelkamp, K., Gasnault, O., Bhattacharjee, P., Clavé, E., Egerland, C. H., Schröder, S., Demir, B., & Lanza, N. (2024) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00671 · Cited by 2
“This is why Explainable AI (XAI) is becoming increasingly popular [28].”
BackgroundExploration of weak-PGML Method for Efficient Stability Control During Machining Operations
Greis, N. P., Nogueira, M. L., Cherukuri, H. P., & Marandi, R. (2024) · Manufacturing Letters · doi:10.1016/j.mfglet.2024.09.181 · Cited by 1
Artificial intelligence and machine learning for foot and ankle disorders
Gupta, S. B., Kour, H., & Antony, P. (2024) · Elsevier eBooks · doi:10.1016/b978-0-443-32892-3.00013-0 · Cited by 3
Dammann, O. (2025) · Springer eBooks · doi:10.1007/978-3-031-82271-1_9 · Cited by 1
On the Interplay of Subset Selection and Informed Graph Neural Networks
Breustedt, N., Climaco, P., Garcke, J., Hamaekers, J., Kutyniok, G., Lorenz, D. A., Oerder, R., & Shukla, C. V. (2025) · Cognitive technologies · doi:10.1007/978-3-031-83097-6_10 · Cited by 1
Self-citationThe Role of AI in Data Anonymization: Can We Trust It with Our Privacy?
Bodimani, M. (2025) · International Journal For Multidisciplinary Research · doi:10.36948/ijfmr.2025.v07i02.42670 · Cited by 1
Clough, L. A., Major, J. D., Seyler, L., Poian, V. D., Theiling, B., & McKinney, B. A. (2025) · Frontiers in Astronomy and Space Sciences · doi:10.3389/fspas.2025.1651953 · Cited by 2
Le, A. T. H., Shvekher, T., Nguyen, L., & Krylov, S. N. (2025) · ChemBioChem · doi:10.1002/cbic.202500678 · Cited by 3
Inter-Pol: An Interpretable Machine Learning Framework for Solvent Polarity Prediction
Ugurlu, S. Y. (2025) · Journal of Solution Chemistry · doi:10.1007/s10953-025-01508-6 · Cited by 1
ElGhawi, R., Winkler, A. J., Reimers, C., Schall, A., Gensheimer, J., & Kraft, B. (2025) · Machine Learning Earth · doi:10.1088/3049-4753/ae2279 · Cited by 4
“…ML techniques, which enhance model transparency by identifying the internal decision-making processes of ML models (Lipton 2018, Samek et al 2019, Roscher et al 2020, Marcinkevicˇs and Vogt 2023), we evaluate whether these ML models capture the correct imposed biophysical relationships and…”
Chen, C., Hu, X., Chen, Y., Ma, S., Yi, P., Zhou, Q., & Wen, J. (2025) · Powder Technology · doi:10.1016/j.powtec.2025.121943 · Cited by 1
Epistemic virtues and ethics of explanation in machine learning
Naser, M. Z., & Naser, Z. K. (2025) · AI and Ethics · doi:10.1007/s43681-025-00869-4 · Cited by 4
“…across real-world applications, particularly in fields where stakeholders require justifiable decisions or must ensure oversight under regulatory constraints [3]. in reporting algorithmic limitations, thoroughness in testing, and sincerity in acknowledging where and why uncertainty arises [10 ].”
Mining the gaps: Deciphering Alzheimer’s biology through AI-driven reconciliation
Funk, C. C., Paterson, T., Bangs, A., Cannon, D. M., Savage, G., Ringger, E. K., & Hood, L. (2025) · The Journal of Prevention of Alzheimer s Disease · doi:10.1016/j.tjpad.2025.100402 · Cited by 6
“Surveys by Leist et al. [37]., Freiesleben et al. [38]., and Roscher et al. [39]. emphasize the importance of interpretability for scientific discovery.”
Prediction of Excavation-Induced Displacement Using Interpretable and SSA-Enhanced XGBoost Model
You, G., Zhang, F., Guo, D., Yan, A., Fu, Q., & He, Z. (2025) · Buildings · doi:10.3390/buildings15234372 · Cited by 1
“Second, many existing ML studies operate as “black boxes,” providing predictions without engineering insights [41,42].”
Jian, F., Chen, X., Wang, M., Guo, Z., Li, X., Jian, H., Ji, R., Liang, L., Yu, Z. Y., & Chen, Y. (2025) · Frontiers in Pharmacology · doi:10.3389/fphar.2025.1703976 · Cited by 1
“This enhanced accuracy is likely attributable to the machine learning algorithm ’ s ability to capture complex, nonlinear interactions among renal, hepatic, and hematological parameters (Roscher et al., 2020).”
Cui, P., Xue, Y., & Wang, Y. (2025) · Results in Engineering · doi:10.1016/j.rineng.2025.107414 · Cited by 1
Bruschi, D., Corato, M. D., Ferrara, A., & Salini, S. (2025) · Applied Stochastic Models in Business and Industry · doi:10.1002/asmb.70061 · Cited by 2
Asli, H. H., Brake, N. A., Nikookar, M., Jahangir, M. S., & Feizbahr, M. (2026) · Journal of Infrastructure Preservation and Resilience · doi:10.1186/s43065-026-00178-y · Cited by 3
Review on reliability of intelligent autonomous systems
Liu, J., Zheng, S., Chen, Y., Xu, D., Wang, C., Xiang, W., Xiao, X., & Lin, J. (2026) · Journal of Reliability Science and Engineering · doi:10.1088/3050-2454/ae4d4b · Cited by 4
“Rather than relying on purely rigid ante-hoc constraints, future designs should synergize interpretable, physics-aware front-ends with flexible deep learning back-ends [163].”
Mathieu, J.-P., Kronwitter, S., Duddeck, F. M. E., Garcke, J., & Vielhaber, M. (2026) · Computers in Industry · doi:10.1016/j.compind.2026.104466 · Cited by 1
Self-citationWang, C., Wang, Z., Deng, R., Huang, S., Hu, Y., Li, D., Peng, X., Long, X., & Zhang, J. (2026) · Bioresource Technology · doi:10.1016/j.biortech.2026.134640 · Cited by 1
On the complementary roles of XVARS and SHAP in explainable AI
Panigrahi, B., Razavi, S., Doig, L. E., Gupta, H., & Liber, K. (2026) · Environmental Modelling & Software · doi:10.1016/j.envsoft.2026.107007 · Cited by 4
Interpretable machine learning reveals how climate shapes precipitation isotopes across China
Wang, T., Dai, Y., Zhao-qiang, Z., Tu, X.-J., & Lin, K.-R. (2026) · Advances in Climate Change Research · doi:10.1016/j.accre.2026.05.014 · Cited by 1
Zeng, B., Niu, J., Yang, G., Ouyang, M., Huang, G., Chen, W., & Zheng, J. (2026) · Frontiers in Marine Science · doi:10.3389/fmars.2026.1843485 · Cited by 1
Hu, L., Neidhardt, H., Braun, A., & Hochschild, V. (2026) · Forests · doi:10.3390/f17060707 · Cited by 1
“In contrast, interpretable machine learning approaches can improve the representation of nonlinear environmental relationships while preserving the complexity of urban systems [31].”
Gkologkinas, G. D., Protopapadakis, E. E., Stamou, A., Tavantzis, I., Dosiou, A., Skalidi, I., & Stylianidis, E. (2026) · Remote Sensing · doi:10.3390/rs18152463 · Cited by 1
Rasak, A., & Ifada, S. (2026) · Journal of Engineering and Applied Science · doi:10.1186/s44147-026-01184-3 · Cited by 1
“Despite these advances, a persistent gap remains in the literature: many current models operate as “black boxes,” prioritizing predictive precision over physical interpretability [7].”
Zhang, F., Sheng, K., Chen, T., Hou, J., & Mei, X. (2026) · Agriculture · doi:10.3390/agriculture16151662 · Cited by 1
KGRAT: An IEC-Informed Knowledge Graph Attention Representation for Power Transformer DGA Diagnosis
Fan, H., Chen, B., Li, Z., Liu, B., & Yang, Y. (2026) · Electronics · doi:10.3390/electronics15163566 · Cited by 1
Sunghyun, M., Im, P., Choi, H., Lee, S., Kim, H. Y., Lee, K.-Y., Han, S., & Woo, S. (2026) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2026.112270
Exploring New Redshift Indicators for Radio-Powerful AGN
Carvajal, R., Matute, I., Afonso, J., Amarantidis, S., Barbosa, D., Cunha, P. A. C., & Humphrey, A. (2021) · Galaxies · doi:10.3390/galaxies9040086 · Cited by 14
“Feature importance [36] can be derived, mostly for Tree-Based models, i.”
BackgroundIskandar, I., & Ahmad, A. (2022) · JISAE JOURNAL OF INDONESIAN STUDENT ASSESMENT AND EVALUATION · doi:10.21009/jisae.v8i2.28936 · Cited by 1
“(Fukada & Seyama, 2022) This approach requires lecturers to manage to learn well so they get a team that can solve the problem completely.(Roscher et al., 2020) Thus, the scientific learning approach requires active involvement in responding to learning changes by optimizing learning resources optimally.”
BackgroundYang, Q., Nan, F., Liu, X., Liu, Q., Lv, J., Feng, J., Wang, F., & Xie, S. (2022) · Plants · doi:10.3390/plants11243485 · Cited by 2
Klasifikasi Gambar Bahan Makanan untuk Penderita Buta Warna
Tedjo, R. T., Sambul, A. M., & Lumenta, A. S. M. (2022) · E-JOURNAL TEKNIK ELEKTRO DAN KOMPUTER · doi:10.35793/jtek.11.2.2022.37794 · Cited by 1
Computational modeling of human multisensory spatial representation by a neural architecture
Domenici, N., Sanguineti, V., Morerio, P., Campus, C., Bue, A. D., Gori, M., & Murino, V. (2023) · PLoS ONE · doi:10.1371/journal.pone.0280987 · Cited by 1
“Specifically, the interpretability of neural networks is an open issue in the Machine Learning community [42], and, as a general rule, the more extensive the network, the lower its intelligibility.”
BackgroundOn the FPGA Implementation of Capsule Networks
Latshaw, J. A., & Popescu, D. C. (2023) · International Symposium on Signals, Circuits and Systems · doi:10.1109/isscs58449.2023.10190946 · Cited by 1
“Over the past decade, machine learning has become a mainstream approach for solving problems in various engineering and science areas [1].”
BackgroundMachine Learning Based Fluid-Transportation Monitoring and Controlling
Bhoite, K. L., Bhosle, S. M., Mirajkar, R., More, R., & Kolekar, S. M. (2023) · International Journal on Recent and Innovation Trends in Computing and Communication · doi:10.17762/ijritcc.v11i9s.7455 · Cited by 1
Explainable Deep Learning Models for Healthcare Decision Support
(2023) · International Journal of Advances in Computer Science and Technology · doi:10.30534/ijacst/2023/0112102023 · Cited by 4
“They believe that interpretability, particularly in situations where the model's advice directly affects patient care, is a crucial component in fostering confidence and acceptance among physicians [11].”
Quantifying Actionability: Evaluating Human-Recipient Models
Kelechi, N., & Jiao, L. (2023) · IEEE Access · doi:10.1109/access.2023.3324906 · Cited by 1
“We know that some ML applications have a greater requirement of R-user actionability than others [10], [33], which can have a downstream impact on actionability considerations when making data selection and feature engineering decisions.”
BackgroundThree-Dimensional Information Modeling Based on Incomplete Data for Anchor Engineering
Zhang, S., Hu, W., Liang, Z., Junjie, Y., Yusen, Z., Liu, Z., & Cuiying, Z. (2023) · IEEE Access · doi:10.1109/access.2023.3329067 · Cited by 1
Trustworthy Medical Operational AI: Marrying AI and Regulatory Requirements
Berns, F., Zimmermann, G., Borgelt, C., Heilig, N., Kirchhoff, J., & Stumpe, F. (2023) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata59044.2023.10386683 · Cited by 2
“Although the resulting concept of transparency encompasses the AI pipeline as a whole [12], an essential step towards transparency is to explicate the meaning and context of the underlying data of the system.”
BackgroundNapoli, E. D., Wu, X., Bornhake, T., & Kowalski, P. M. (2024) · Frontiers in Applied Mathematics and Statistics · doi:10.3389/fams.2024.1355726 · Cited by 1
Vers l’XAI sémantique – la troisième vague de l’intelligence artificielle explicable
Bollaert, M., & Coppin, G. (2024) · Ingénierie cognitique · doi:10.21494/iste.op.2024.1147 · Cited by 1
Simamora, N. N., Kimball, D. F. J., Maulana, R., & Sunarmi, N. (2024) · EduFisika Jurnal Pendidikan Fisika · doi:10.59052/edufisika.v9i1.29681 · Cited by 4
“Natural Science as a process includes an understanding of how scientific information is obtained, tested, and validated (Tshitoyan et al., 2019; Roscher et al., 2020).”
BackgroundGaining Insights with Deep Learning on Small Scale Cancer Detection
Doda, D. K., N, K. R. B., & Sahoo, J. (2024) · International Conference on Artificial Intelligence and Machine Learning Applications Theme: Healthcare and Internet of Things (AIMLA) · doi:10.1109/aimla59606.2024.10531421 · Cited by 1
“It lets researchers create insights into the molecular biology of cancer in an extra green, powerful, and unobtrusive way[19].”
BackgroundInsights into Nanodiamond from Machine Learning
Barnard, A. S. (2024) · Topics in applied physics · doi:10.1007/978-3-031-47556-6_2 · Cited by 1
SANCHEZ, A. E. R. (2024) · Revista Colombiana de Filosofía de la Ciencia · doi:10.18270/rcfc.4288 · Cited by 2
Urban Mobility Planning and Path Optimization in Mobility as a Service (MaaS) Using Machine Learning
Ali, G., & Ahmad, M. (2024) · Contributions to finance and accounting · doi:10.1007/978-3-031-67547-8_21 · Cited by 1
SVF: Support Vector Federation
Polato, M., Esposito, R., & Sciandra, L. (2025) · IEEE Access · doi:10.1109/access.2025.3562053 · Cited by 3
“Although, broadly speaking, neural networks are just the hottest topic in machine learning, there exists a non-negligible portion of application scenarios in which ‘‘classical’’ machine learning approaches are still used [20] especially when explainability plays an important role [21], [22], [23].”
Human-Friendly Explanations Checklist for Reinforcement Learning: XRL H-F-E Checklist
Olivas, D. A. C., & Martínez-Villaseñor, L. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-97910-1_21 · Cited by 1
On the Space of Coefficients of a Feedforward Neural Network
Valluri, D., & Campbell, R. (2023) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn54540.2023.10191403 · Cited by 3
“Explainable AI is useful for examining ML results in a scientific context [5] and for explaining ML results to stakeholders in enterprise contexts [6].”
BackgroundAnalysis of Students’ Online Interactions in the Covid Era from the Perspective of Anomaly Detection
Otero, J., Sánchez, L., Junco, L., & Couso, I. (2021) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-87872-6_30 · Cited by 1
Time-Series Analysis and Forecasting of Power Consumption using Gaussian Process Regression
Zimmer, M., Pesch, T., & Benigni, A. (2021) · International Conference on Smart Energy Systems and Technologies (SEST) · doi:10.1109/sest50973.2021.9543253 · Cited by 1
Information Visualisation for Antibiotic Detection Biochip Design and Testing
Craig, P., Ng, R., Tefsen, B., Linsen, S. E. V., Liu, Y., & Hendel, J. (2022) · Processes · doi:10.3390/pr10122680 · Cited by 1
FEPC: Fairness Estimation Using Prototypes and Critics for Tabular Data
Giloni, A., Grolman, E., Elovici, Y., & Shabtai, A. (2022) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr56361.2022.9956582 · Cited by 2
“, records that grasp the correlations found by the model [17].”
BackgroundMethodTen Years of DataMod: The Synergy of Data-Driven and Model-Based Approaches
Cerone, A. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-16011-0_2 · Cited by 1
Banda, T. M., Zăvoianu, A.-C., Petrovski, A., Wöckinger, D., & Bramerdorfer, G. (2023) · ACM Transactions on Evolutionary Learning and Optimization · doi:10.1145/3597618 · Cited by 3
Nadeem, A., Verwer, S., & Yang, S. J. (2023) · Advances in information security · doi:10.1007/978-3-031-29269-9_6 · Cited by 1
Insights into cosmological structure formation with machine learning.
Lucie-Smith, L. (2020) · OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information) · doi:10.2172/1771179 · Cited by 2
“Recently, there have been several applications in the field of natural sciences that use machine learning for scientific discovery (Roscher et al. 2019).”
BackgroundExplanation from SpecificationPreprint
Naik, H., & Turán, G. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.07179 · Cited by 3
“2017) on theoryguided data science and (Roscher et al. 2020) on explainability aspects of current science research.”
BackgroundZeng, J., Xu, H. J., Chen, Y., & Zhang, D. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.00009 · Cited by 1
“, 1 2 = and 1 2 , and nondimensionalizing the above equation based on equation (6), the theoretically derived dimensionless PDEs can be written as:”
BackgroundInfluentialA Clustering-aided Ensemble Method for Predicting Ridesourcing Demand in ChicagoPreprint
Zhang, X., & Zhao, X. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.03433 · Cited by 1
“With the development of machine learning models, there is a growing trend to make machine-learning results more interpretable and explainable (Roscher et al., 2020).”
BackgroundInterpretation and Simplification of Deep ForestPreprint
Kim, S., Jeong, M., & Ko, B. C. (2020) · doi:10.36227/techrxiv.11661246 · Cited by 1
Increasing Trust and Fairness in Machine Learning Applications within the Mortgage IndustryPreprint
van Zetten, W., Ramackers, G. J., & Hoos, H. H. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4117395 · Cited by 1
Solving the challenges of concept drift in data stream classification.
Hu, H. (2022) · ThinkIR: The University of Louisville's Institutional Repository (University of Louisville) · doi:10.18297/etd/3947 · Cited by 3
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 · Cited by 2
Explainable Machine Learning for Hydrocarbon Prospect RiskingPreprint
Mustafa, A., AlRegib, G., & Koster, K. (2023) · doi:10.31223/x5jd5d · Cited by 1
Regulação da inteligência artificial na saúde
Dourado, D. D. A. (2024) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/t.5.2024.tde-23042024-111255 · Cited by 10
Towards an implementation of an AutoML tool for manufacturing
Gerling, A. (2022) · theses.fr (ABES) · doi:10.70675/c70c0375z5232z4ea2zb0cazabab20ce709a · Cited by 1
On the Use of Interpretable Machine Learning for the Management of Data QualityPreprint
Karanika, A., Oikonomou, P., Kolomvatsos, K., & Anagnostopoulos, C. B. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.14677 · Cited by 3
“The authors of [33] review explainable machine learning in view of applications in the natural sciences and discuss three core elements i.e., transparency, interpretability, and explainability.”
BackgroundDiscovery of the Hidden State in Ionic Models Using a Domain-Specific Recurrent Neural NetworkPreprint
Iravanian, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.07388 · Cited by 1
“In the last few years, scientific machine learning has emerged as a powerful alternative to the traditional methodology in the study of dynamical systems [19].”
Molecular origin of blood-based infrared fingerprintsPreprint
Voronina, L., Leonardo, C., Mueller-Reif, J. B., Geyer, P. E., Huber, M., Trubetskov, M. K., Kepesidis, K. V., Behr, J., Mann, M., Krausz, F., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.00765
“Both spectral and molecular information was used to build explainable classification models for lung cancer detection (46).”
White-box Deep Neural Network Prediction of Genome-Wide Transcriptome SignaturesPreprint
Magnusson, R., Tegnér, J., & Gustafsson, M. (2021) · bioRxiv · doi:10.1101/2021.02.11.430730
“A black-box model does not lend itself to interpretable and meaningful representations which may also make the model more susceptible for adversarial attacks [27], [28].”
BackgroundInterpretable machine learning approach for predicting COVID-19 risk status of an individual
Onoja, A., Ejiwale, M. O., & Rewane, A. (2021) · Transactions on Networks and Communications · doi:10.14738/tnc.92.9760
Al-Roomi, A. R. (2021) · IEEE Systems Man and Cybernetics Magazine · doi:10.1109/msmc.2020.3036365
“It could be a legal issue if there is a mistake in a medical diagnosis or if there is an accident where self-driving cars are involved [3], [4].”
Background
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.