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 201–300 of 999
The emergent role of explainable artificial intelligence in the materials sciences
Liu, T., & Barnard, A. S. (2023) · Cell Reports Physical Science · doi:10.1016/j.xcrp.2023.101630 · Cited by 47
Bridging adaptive management and reinforcement learning for more robust decisions
Chapman, M., Xu, L., Lapeyrolerie, M., & Boettiger, C. (2023) · Philosophical Transactions of the Royal Society B Biological Sciences · doi:10.1098/rstb.2022.0195 · Cited by 45
Roscher, R., Bohn, B., Duarte, M. F., & Garcke, J. (2020) · ISPRS annals of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-annals-v-3-2020-817-2020 · Cited by 42
“We continue our discussions from (Roscher et al., 2020) and consider the usefulness of explainable machine learning not only for deriving scientific output but also for tackling known remote sensing challenges.”
BackgroundMethodInfluentialSelf-citationScientific intuition inspired by machine learning-generated hypotheses
Friederich, P., Krenn, M., Tamblyn, I., & Aspuru‐Guzik, A. (2021) · Machine Learning Science and Technology · doi:10.1088/2632-2153/abda08 · Cited by 57
“The methods used in these cases enforce information bottlenecks or interpretable transformations in the ML model that then can inspire scientific understanding for human researchers [14].”
BackgroundMethodExplainable Machine Learning with Prior Knowledge: An Overview
Beckh, K., Müller, S., Jakobs, M., Toborek, V., Tan, H., Fischer, R., Welke, P., Houben, S., & von Rueden, L. (2021) · Lancaster EPrints (Lancaster University) · doi:10.48550/arxiv.2105.10172 · Cited by 68
“The integration of prior knowledge was already motivated in the 2000s in connection with support vector machines [34] and has been revisited recently for scientific discoveries from data and ML output [26; 59].”
Deep neural network prediction of genome-wide transcriptome signatures – beyond the Black-box
Magnusson, R., Tegner, J. N., & Gustafsson, M. (2022) · npj Systems Biology and Applications · doi:10.1038/s41540-022-00218-9 · Cited by 31
“…model does not lend itself to interpretable and meaningful representations, potentially making the model more susceptible to adversarial attacks 36,37 , Recently, it has become increasingly clear that deep neural networks (DNNs) have the potential to identify biologically meaningful molecular…”
Wang, A., Mahmoud, M. S., Czasny, M., & Gurlo, A. (2022) · Integrating materials and manufacturing innovation · doi:10.1007/s40192-021-00247-y · Cited by 40
Titz, M., Pütz, S., & Witthaut, D. (2023) · Applied Energy · doi:10.1016/j.apenergy.2023.122351 · Cited by 46
Letard, M., Lague, D., Guennec, A. L., Lefèvre, S., Feldmann, B., Leroy, P., Girardeau-Montaut, D., & Corpetti, T. (2023) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2023.11.022 · Cited by 41
“In contrast, the mean number of returns characterizes vegetation and artificial elements .”
BackgroundMethodAboulola, O. I., Alabdulqader, E. A., Alarfaj, A. A., Alsubai, S., & Kim, T.-H. (2024) · IEEE Access · doi:10.1109/access.2024.3380895 · Cited by 44
“The incorporation of explanation techniques enhances transparency, interpretability, explanatory capacity, domain knowledge integration, and scientific coherence of models [27], addressing the common perception of prediction methods as black boxes.”
BackgroundInterpretable Landslide Susceptibility Evaluation Based on Model Optimization
Qiu, H., Xu, Y., Tang, B., Su, L., Li, Y., Yang, D., & Ullah, M. (2024) · Land · doi:10.3390/land13050639 · Cited by 44
Cybersecurity Knowledge Extraction Using XAI
Šarčević, A., Pintar, D., Vranić, M., & Krajna, A. (2022) · Applied Sciences · doi:10.3390/app12178669 · Cited by 41
Federated explainable artificial intelligence (fXAI): a digital manufacturing perspective
Kusiak, A. (2023) · International Journal of Production Research · doi:10.1080/00207543.2023.2238083 · Cited by 34
“In the survey paper, Roscher et al. (2020) focused on three characteristics of XAI, transparency, interpretability, and integration of domain knowledge.”
BackgroundA review of metal-organic frameworks and polymers in mixed matrix membranes for CO 2 capture
Christensen, C., Hansen, N., Motadayen, M., Lock, N., Henriksen, M. L., & Quinson, J. (2025) · Beilstein Journal of Nanotechnology · doi:10.3762/bjnano.16.14 · Cited by 35
Kakhani, N., Taghizadeh‐Mehrjardi, R., Omarzadeh, D., Ryo, M., Heiden, U., & Scholten, T. (2025) · European Journal of Soil Science · doi:10.1111/ejss.70071 · Cited by 33
“This is crucial, since many scientists apply ML methodologies to optimise/generate scientific findings (Roscher et al. 2020).”
Interpretable Optimization: Why and How We Should Explain Optimization Models
Lumbreras, S., & Ciller, P. (2025) · Applied Sciences · doi:10.3390/app15105732 · Cited by 40
Schorr, C., Goodarzi, P., Chen, F., & Dahmen, T. (2021) · Applied Sciences · doi:10.3390/app11052199 · Cited by 34
“Even the definition of ‘explanation’ in this context alone is not without controversy; for a comprehensive attempt to clarify the terminology refer to [38].”
BackgroundSecondary control activation analysed and predicted with explainable AI
Kruse, J., Schäfer, B., & Witthaut, D. (2022) · Electric Power Systems Research · doi:10.1016/j.epsr.2022.108489 · Cited by 36
Betancourt, C., Stomberg, T. T., Edrich, A.-K., Patnala, A., Schultz, M. G., Roscher, R., Kowalski, J., & Stadtler, S. (2022) · Geoscientific model development · doi:10.5194/gmd-15-4331-2022 · Cited by 46
Self-citationSteering the interpretability of decision trees using lasso regression - an evolutionary perspective
Czajkowski, M., Jurczuk, K., & Krętowski, M. (2023) · Information Sciences · doi:10.1016/j.ins.2023.118944 · Cited by 29
A novel approach to minimal reservoir computing
Ma, H., Prosperino, D., & Rath, C. W. (2023) · Scientific Reports · doi:10.1038/s41598-023-39886-w · Cited by 41
“Due to our choice of architecture, the reservoir states for each feature can be obtained separately: (4) r(t + 1) = A · r(t)+Win ·Wout · r̃(t) .”
BackgroundPradeep, P., Caro-Martínez, M., & Wijekoon, A. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.124733 · Cited by 51
Artificial intelligence in food and nutrition evidence: The challenges and opportunities
Bailey, R. L., MacFarlane, A. J., Field, M. S., Tagkopoulos, I., Baranzini, S. E., Edwards, K. M., Rose, C. J., Schork, N. J., Singhal, A., Wallace, B., et al. (2024) · PNAS Nexus · doi:10.1093/pnasnexus/pgae461 · Cited by 36
“However, two major challenges continue to prevent their integration into broader clinical practice (26).”
Bilgilioğlu, S. S., Gezgin, C., İban, M. C., BİLGİLİOĞLU, H., Gündüz, H. İ., & Arslan, Ş. (2025) · Applied Sciences · doi:10.3390/app15063139 · Cited by 34
Physics-informed generative neural network: an application to troposphere temperature prediction
Chen, Z., Gao, J., Wang, W., & Yan, Z. (2021) · Environmental Research Letters · doi:10.1088/1748-9326/abfde9 · Cited by 35
Stadtler, S., Betancourt, C., & Roscher, R. (2022) · Machine Learning and Knowledge Extraction · doi:10.3390/make4010008 · Cited by 35
“[31], an essential component is domain knowledge, which is needed to increase models’ and results’ explainability and enhance scientific consistency.”
BackgroundSelf-citationKellner, L., Stender, M., Polach, F. V. B. U., & Ehlers, S. (2022) · Ocean Engineering · doi:10.1016/j.oceaneng.2022.111396 · Cited by 30
Schneider, R., Bonavita, M., Geer, A., Arcucci, R., Dueben, P. D., Vitolo, C., Saux, B. L., Demir, B., & Mathieu, P.-P. (2022) · npj Climate and Atmospheric Science · doi:10.1038/s41612-022-00269-z · Cited by 40
“These tools are known as explain-able Arti fi cial Intelligence (AI) 9 .”
MethodGreis, N. P., Nogueira, M. L., Bhattacharya, S., Spooner, C., & Schmitz, T. L. (2022) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-022-01999-w · Cited by 32
“Roscher et al. (2020) approach informed machine learning from the perspective of its ability to extract and explain novel scientific results.”
BackgroundAn Explainable Machine Learning Model For Lumpy Skin Disease Occurrence Detection
Jain, A. K., Tiwari, R. G., Ujjwal, N., & Singh, A. (2022) · International Conference on Data Analytics for Business and Industry (ICDABI) · doi:10.1109/icdabi56818.2022.10041665 · Cited by 31
“To solve this issue, we need Explainable AI models to lay out the specifics and rationale behind how AI works so that it can be better comprehended by non-technical audiences[7], [8].”
BackgroundWang, Z., Xian, W., Li, Y., & Xu, H. (2023) · Computational Mechanics · doi:10.1007/s00466-023-02328-5 · Cited by 28
“For problems with a high dimensional input space and high nonlinear responses, the ML model, such as DNN, requires a large amount of training data, which are not easily available in engineering applications [43, 44].”
MethodInterpretable Machine Learning for Predicting Customer Churn in Retail Banking
Murindanyi, S., Mugalu, B. W., Nabende, J. N., & Marvin, G. (2023) · International Conference on Trends in Electronics and Informatics (ICOEI) · doi:10.1109/icoei56765.2023.10125859 · Cited by 31
“An ML model’s ability to be understood is referred to as interpretability [9].”
BackgroundA survey of dialogic emotion analysis: Developments, approaches and perspectives
Gan, C., Zheng, J., Zhu, Q., Cao, Y., & Zhu, Y. (2024) · Pattern Recognition · doi:10.1016/j.patcog.2024.110794 · Cited by 35
Sheik, A. G., Malla, M. A., Srungavarapu, C. S., Patan, A. K., Kumari, S., & Bux, F. (2024) · Journal of Water Process Engineering · doi:10.1016/j.jwpe.2024.106185 · Cited by 27
Physics-Informed Machine Learning in Design and Manufacturing: Status and Challenges
Pan, L., Li, G., Zhu, T., Liu, D., Wang, Y., & Lu, Y. (2025) · Journal of Computing and Information Science in Engineering · doi:10.1115/1.4070100 · Cited by 43
A Hybrid Artificial Neural Network to Estimate Soil Moisture Using SWAT+ and SMAP Data
Breen, K. H., James, S. C., White, J. D., Allen, P. M., & Arnold, J. G. (2020) · Machine Learning and Knowledge Extraction · doi:10.3390/make2030016 · Cited by 28
“Feature engineering is a common practice to incorporate physical knowledge into training data [1].”
BackgroundApplications of Physics-Informed Scientific Machine Learning in Subsurface Science: A Survey
Sun, A. Y., Yoon, H., Shih, C. Y., & Zhong, Z. (2022) · Chapman & Hall/CRC eBooks · doi:10.1201/9781003143376-5 · Cited by 28
Sagayaraj, M. J., Jithesh, V., & Roshani, D. (2021) · International Conference on Artificial Intelligence and Smart Energy (ICAIS) · doi:10.1109/icais50930.2021.9395855 · Cited by 29
“Though connectionist techniques are quite popular, they suffer from explainability [1, 4] aspects on decision arrived at compared to conventional symbolic”
BackgroundDeng, Q., Hu, J., Wang, L., Liu, Y., Guo, Y., Xu, T., & Pu, X. (2021) · Chemometrics and Intelligent Laboratory Systems · doi:10.1016/j.chemolab.2021.104331 · Cited by 28
Naik, R. R., Tiihonen, A., Thapa, J., Batali, C., Liu, Z., Sun, S., & Buonassisi, T. (2022) · npj Computational Materials · doi:10.1038/s41524-022-00751-5 · Cited by 31
Data-driven causal inference of process-structure relationships in nanocatalysis
Ting, J. Y. C., & Barnard, A. S. (2022) · Current Opinion in Chemical Engineering · doi:10.1016/j.coche.2022.100818 · Cited by 33
An Analysis Method for Interpretability of Convolutional Neural Network in Bearing Fault Diagnosis
Guo, L., Gu, X., Yu, Y., Duan, A., & Gao, H. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3334350 · Cited by 30
“CNN-based models are generally considered to be black box models [21], [22], meaning that the higher order features learned by the model are difficult to articulate in a comprehensible way.”
BackgroundAldeia, G. S. I., & de França, F. O. (2022) · Genetic Programming and Evolvable Machines · doi:10.1007/s10710-022-09435-x · Cited by 38
“1] MLP Hidden_layer_sizes activation [(50, ), (50, 100, ), (100, ), (100, 100, )] [identity, logistic, tanh, relu] SVM Kernel degree [linear, rbf , poly] [1, 2, 3, 4] k-NN n_neighbors [3, 5, 7, 9, 11, 17, 19, 23, 29, 31] Operon Population_size generations [100, 250, 500] [100, 250, 500] ITEA Popsize gens [100, 250, 50…”
Backgrounddos Santos, J. P. M., & dos Santos, J. D. M. (2024) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2024.1305164 · Cited by 36
“Hence, the present study uses xAI methods to explain and interpret the ANN, aiming to extract a comprehensible model of brand perception (Roscher et al., 2020).”
MethodSweet, L., Athanasiadis, I. N., van Bree, R., Castellano, A., Martre, P., Paudel, D., Ruane, A. C., & Zscheischler, J. (2025) · One Earth · doi:10.1016/j.oneear.2025.101233 · Cited by 40
MoËT: Mixture of Expert Trees and its application to verifiable reinforcement learning
Vasić, M., Petrović, A., Wang, K., Nikolić, M., Singh, R., & Khurshid, S. (2022) · Neural Networks · doi:10.1016/j.neunet.2022.03.022 · Cited by 47
“Explainable Machine Learning: There has been a lot of recent interest in explaining decisions of black-box models [25, 26, 27].”
BackgroundImproving the performance of the intrusion detection systems by the machine learning explainability
Dang, Q.-V. (2021) · International Journal of Web Information Systems · doi:10.1108/ijwis-03-2021-0022 · Cited by 32
Learning quantum dynamics with latent neural ordinary differential equations
Choi, M., Flam-Shepherd, D., Kyaw, T. H., & Aspuru‐Guzik, A. (2022) · Physical Review A · doi:10.1103/physreva.105.042403 · Cited by 38
Papacharalampous, G., Tyralis, H., Doulamis, A. D., & Doulamis, N. D. (2023) · Hydrology · doi:10.3390/hydrology10020050 · Cited by 36
Ding, N., Yuan, Z., Ma, Z., Wu, Y., & Yin, L. (2024) · Molecules · doi:10.3390/molecules29153512 · Cited by 30
Earth's record-high greenness and its attributions in 2020
Zhang, Y., Mao, J., Sun, G., Guo, Q., Atkins, J., Li, W., Jin, M., Song, C., Xiao, J., Hwang, T., et al. (2024) · Remote Sensing of Environment · doi:10.1016/j.rse.2024.114494 · Cited by 27
“This contrasts with machine learning models that are primarily driven by data and statistical approaches and lack of explainability as a “ black box ” (Roscher et al., 2020).”
Present and future of machine learning in breast surgery: systematic review
Soh, C. L., Shah, V., Rad, A. A., Vardanyan, R., Zubarevich, A., Torabi, S., Weymann, A., Miller, G., & Malawana, J. (2022) · British journal of surgery · doi:10.1093/bjs/znac224 · Cited by 29
Prolog-based agnostic explanation module for structured pattern classification
Nápoles, G., Hoitsma, F., Knoben, A., Jastrzębska, A., & León, M. (2022) · Information Sciences · doi:10.1016/j.ins.2022.12.012 · Cited by 37
Sensors and chemometrics in downstream processing
Dürauer, A., Jungbauer, A., & Scharl, T. (2024) · Biotechnology and Bioengineering · doi:10.1002/bit.28499 · Cited by 23
“In the machine learning community, a lot of current research is attempting to explain what is going on inside prediction models (Roscher et al., 2020; Zhong et al., 2022).”
Interpretable Deep-Learning Unveils Structure–Property Relationships in Polybenzenoid Hydrocarbons
Weiss, T., Wahab, A., Bronstein, A. M., & Gershoni-Poranne, R. (2023) · The Journal of Organic Chemistry · doi:10.1021/acs.joc.2c02381 · Cited by 24
Luo, Z., Qi, X., Sun, C. T., Dong, Q., Gu, J., & Gao, X. (2024) · Building and Environment · doi:10.1016/j.buildenv.2024.111394 · Cited by 26
Real-Time Fraud Detection Using Machine Learning
Borketey, B., & Borketey, D. (2024) · Journal of Data Analysis and Information Processing · doi:10.4236/jdaip.2024.122011 · Cited by 32
Understanding predictions of drug profiles using explainable machine learning models
König, C., & Vellido, A. (2024) · BioData Mining · doi:10.1186/s13040-024-00378-w · Cited by 30
“This is a strong limitation when the interpretability of the model is a requirement, for example when experts are interested in exploring the feature space for determining feature importance [14].”
BackgroundComputer vision tasks for intelligent aerospace perception: An overview
Chen, H., Sun, Q., Li, F., & Tang, Y. (2024) · Science China Technological Sciences · doi:10.1007/s11431-024-2714-4 · Cited by 30
“Therefore, mechanism models can incorporate the basic principle of the research process and integrate prior knowledge into the learning process, thus improving generalizability, flexibility, and interpretability [173].”
Alatefi, S., Agwu, O., & Alkouh, A. (2024) · Results in Engineering · doi:10.1016/j.rineng.2024.103328 · Cited by 25
Operationally meaningful representations of physical systems in neural networks
Nautrup, H. P., Metger, T., Iten, R., Jerbi, S., Trenkwalder, L. M., Wilming, H., Briegel, H. J., & Renner, R. (2022) · Machine Learning Science and Technology · doi:10.1088/2632-2153/ac9ae8 · Cited by 37
Physics-Informed Gaussian Process Regression for Optical Fiber Communication Systems
Nevin, J. W., Vaquero-Caballero, F. J., Ives, D. J., & Savory, S. J. (2021) · Journal of Lightwave Technology · doi:10.1109/jlt.2021.3106714 · Cited by 32
Explainable AI in Aerospace for Enhanced System Performance
Sutthithatip, S., Perinpanayagam, S., Aslam, S., & Wileman, A. (2021) · IEEE/AIAA Digital Avionics Systems Conference (DASC) · doi:10.1109/dasc52595.2021.9594488 · Cited by 35
Causal deep learning models for studying the Earth system
Tesch, T., Kollet, S. J., & Garcke, J. (2023) · Geoscientific model development · doi:10.5194/gmd-16-2149-2023 · Cited by 32
Self-citationZhou, M., Zhou, B., Zhang, Z., Zhou, Z., Liu, J., Li, B., Wang, D., & Wu, T. (2023) · Fire · doi:10.3390/fire6050190 · Cited by 24
Path Spuriousness-aware Reinforcement Learning for Multi-Hop Knowledge Graph Reasoning
Jiang, C., Zhu, T., Zhou, H., Liu, C., Deng, T., Hu, C., & Li, J. (2023) · Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/2023.eacl-main.232 · Cited by 24
“Despite the powerful representational ability shown by embedding-based models, they are limited in many scenarios for the lack of explainability (Roscher et al., 2020; Liu et al., 2017), as one-hop reasoning methods.”
BackgroundDzialas, V., Doering, E., Eich, H., Strafella, A. P., Vaillancourt, D. E., Simonyan, K., van Eimeren, T., & International Parkinson Movement Disorders Society‐Neuroimaging Study Group (2024) · Movement Disorders · doi:10.1002/mds.30002 · Cited by 30
“20,86 Recommendations for Future Research Based on the issues described earlier, we could identify a tremendous gap between the clinical needs of PD management and the use of scienti fi c resources in the realm of neuroimaging-based AI research.”
Schultebraucks, K., & Chang, B. (2020) · Experimental Neurology · doi:10.1016/j.expneurol.2020.113526 · Cited by 28
“…is important for shared decision-making of patients and care providers, it will remain an important challenge for ML approaches to make use of such interpretable ML approaches (Roscher et al., 2020) so that patients can be informed on which clinical variables the predicted outcome is derived from.”
BackgroundNatural Code of Subjective Experience
Суров, И. А. (2022) · Biosemiotics · doi:10.1007/s12304-022-09487-7 · Cited by 24
Schuhmacher, D., Schörner, S., Küpper, C., Großerueschkamp, F., Sternemann, C., Lugnier, C., Kraeft, A., Jütte, H., Tannapfel, A., Reinacher‐Schick, A., et al. (2022) · Medical Image Analysis · doi:10.1016/j.media.2022.102594 · Cited by 26
Nowcasting of fecal coliform presence using an artificial neural network
Pras, A., & Mamane, H. (2023) · Environmental Pollution · doi:10.1016/j.envpol.2023.121484 · Cited by 25
Hanna, J. M., Aguado, J. V., Comas-Cardona, S., Guennec, Y. L., & Borzacchiello, D. (2024) · Composites Part A Applied Science and Manufacturing · doi:10.1016/j.compositesa.2024.108019 · Cited by 35
Identifying epilepsy psychiatric comorbidities with machine learning
Glauser, T. A., Santel, D., DelBello, M. P., Faist, R., Toon, T., Clark, P. O., McCourt, R., Wissel, B. D., & Pestian, J. P. (2019) · Acta Neurologica Scandinavica · doi:10.1111/ane.13216 · Cited by 28
Kranstauber, B., Bouten, W., van Gasteren, H., & Shamoun-Baranes, J. Z. (2022) · Ecological Solutions and Evidence · doi:10.1002/2688-8319.12158 · Cited by 22
Multiscale extrapolative learning algorithm for predictive soil moisture modeling & applications
Chakraborty, D., Başağaoğlu, H., Alian, S., Mirchi, A., Moriasi, D. N., Starks, P. J., & Verser, J. A. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.119056 · Cited by 22
Harnessing Prior Knowledge for Explainable Machine Learning: An Overview
Beckh, K., Müller, S., Jakobs, M., Toborek, V., Tan, H., Fischer, R., Welke, P., Houben, S., & von Rueden, L. (2023) · IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) · doi:10.1109/satml54575.2023.00038 · Cited by 33
Explaining protein–protein interactions with knowledge graph-based semantic similarity
Sousa, R. T., Silva, S., & Pesquita, C. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.108076 · Cited by 29
Mota, B., Faria, P., Ramos, C. A., & Vale, Z. (2025) · Journal of Industrial Information Integration · doi:10.1016/j.jii.2025.100910 · Cited by 31
A Comprehensive Review on Scaling Machine Learning Workflows Using Cloud Technologies and DevOps
Ramesh, G., Pai, T. V., Birau, R., Poojary, K. K., Abhay, Shingad, A. R., Sowjanya, N., Popescu, V., Mitroi, A. T., Chireac, R. M. N., et al. (2025) · IEEE Access · doi:10.1109/access.2025.3599281 · Cited by 39
Tian, Y., Zhao, Y., Li, J., Shen, C., Zhang, Y., Wen, D., Qi, X., Liu, Y., & Chen, D. (2026) · Atmospheric Research · doi:10.1016/j.atmosres.2026.108809 · Cited by 26
Bias, journalistic endeavours, and the risks of artificial intelligence
Leiser, M. R. (2022) · Edward Elgar Publishing eBooks · doi:10.4337/9781839109973.00007 · Cited by 50
Arifuzzaman, M., Qureshi, H. J., Fuhaid, A. F. A., Alanazi, F., Javed, M. F., & Eldin, S. M. (2023) · Journal of Materials Research and Technology · doi:10.1016/j.jmrt.2023.03.218 · Cited by 23
Colangelo, G., Ribó, M., Montiel, E., Domínguez, D., Olivé‐Gadea, M., Muchada, M., García‐Tornel, Á., Requena, M., Pagola, J., Juega, J., et al. (2024) · Stroke · doi:10.1161/strokeaha.123.043691 · Cited by 31
“49 Several ML predictive strategies, such as ours, 50,51 aim to bridge this gap by providing good predictions while offering explainable and interpretable models.”
BackgroundSkeleton-Based Explainable Bodily Expressed Emotion Recognition Through Graph Convolutional Networks
Ghaleb, E., Mertens, A., Asteriadis, S., & Weiß, G. (2021) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/fg52635.2021.9667052 · Cited by 25
“of used models are essential to increase scientific discovery to have consistency with domain knowledge [3].”
MethodComputer Simulations in Science
Alvarado, R. (2023) · Synthese Library/Synthese library · doi:10.1007/978-3-031-38647-3_2 · Cited by 21
Feature-Free Explainable Data Mining in SAR Images Using Latent Dirichlet Allocation
Karmakar, C., Dumitru, C. O., Schwarz, G., & Datcu, M. P. (2020) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2020.3039012 · Cited by 28
“[5] mention [13] as a black-box approach, commenting that it is design-nontransparent, noninterpretable, and nonexplain-able as it neither offers any explanation for its design choices nor applies any domain knowledge to explain its outcomes.”
BackgroundMethodInfluentialLi, J., Sawaragi, T., & Horiguchi, Y. (2021) · SICE Journal of Control Measurement and System Integration · doi:10.1080/18824889.2021.1894040 · Cited by 24
On gray-box modeling for virtual flow metering
Hotvedt, M., Grimstad, B., Ljungquist, D., & Imsland, L. (2021) · Control Engineering Practice · doi:10.1016/j.conengprac.2021.104974 · Cited by 24
“Interpretability is defined as the degree to which a model can be presented in understandable terms to a human (Roscher et al., 2020).”
BackgroundExploring deterministic frequency deviations with explainable AI
Kruse, J., Schäfer, B., & Witthaut, D. (2021) · IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm) · doi:10.1109/smartgridcomm51999.2021.9632335 · Cited by 31
“However, complex ML models are often black-boxes, which impede a scientific understanding of the model structure [14].”
BackgroundActive learning-assisted neutron spectroscopy with log-Gaussian processes
Parente, M. T., Brandl, G., Franz, C., Stuhr, U., Ganeva, M., & Schneidewind, A. (2023) · Nature Communications · doi:10.1038/s41467-023-37418-8 · Cited by 26
Understanding the patterns that neural networks learn from chemical spectra
Rieger, L., Wilson, M., Vegge, T., & Flores, E. (2023) · Digital Discovery · doi:10.1039/d3dd00203a · Cited by 27
“Using NNs for scientific discovery requires understanding how the learned patterns build upon existing scientific principles [38].”
BackgroundOne-Class Classification of Natural Vegetation Using Remote Sensing: A Review
Rapinel, S., & Hubert‐Moy, L. (2021) · Remote Sensing · doi:10.3390/rs13101892 · Cited by 23
On Locality of Local Explanation ModelsPreprint
Ghalebikesabi, S., Ter-Minassian, L., Diaz‐Ordaz, K., & Holmes, C. C. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.14648 · Cited by 48
Insights into Artificial Intelligence Bias: Implications for Agriculture
Mayuravaani, M., Ramanan, A., Perera, M., Senanayake, D., & Vidanaarachchi, R. (2024) · Digital Society · doi:10.1007/s44206-024-00142-x · Cited by 23
“Many effective AI algorithms are called a “black box” approach, making it challenging or impossible to comprehend how the results were reached (Roscher et al., 2020 ).”
An analysis of machine learning algorithms in rotating machines maintenance
Roque, A. D. S., Krebs, V. W., Figueiro, I. C., & Jazdi, N. (2022) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2022.04.202 · Cited by 21
Vargas, C. A., & Hanandeh, A. E. (2022) · International Journal of Pavement Research and Technology · doi:10.1007/s42947-022-00213-7 · Cited by 22
Deep Q‐learning: A robust control approach
Varga, B., Kulcsár, B., & Chehreghani, M. H. (2022) · International Journal of Robust and Nonlinear Control · doi:10.1002/rnc.6457 · Cited by 22
Explainable Deep-Learning-Based Depression Modeling of Elderly Community after COVID-19 Pandemic
Nguyen, H. V., & Byeon, H. (2022) · Mathematics · doi:10.3390/math10234408 · Cited by 19
Li, X., Chen, D., Xu, W., Chen, H., Li, J., & Mo, F. (2023) · Humanities and Social Sciences Communications · doi:10.1057/s41599-023-01505-4 · Cited by 24
“, why the AI models make such predictions with specific inputs), it also transfers knowledge between ‘explainer’ and ‘explainee’, enhancing human understanding of the corresponding domain knowledge (Roscher et al., 2020).”
BackgroundExplainable deep learning: concepts, methods, and new developments
Samek, W. (2023) · Elsevier eBooks · doi:10.1016/b978-0-32-396098-4.00008-9 · Cited by 26
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.