Local interpretation of machine learning models in remote sensing with SHAP: the case of global climate constraints on photosynthesis phenology

References

• Aguilos, M., B. Hérault, B. Burban, F. Wagner, and D. Bonal. 2018. “What Drives Long-Term Variations in Carbon Flux and Balance in a Tropical Rainforest in French Guiana?” Agricultural and Forest Meteorology 253: 114–123. doi:10.1016/j.agrformet.2018.02.009.
   Web of Science ®Google Scholar
• Ahmad, R., B. Yang, G. Ettlin, A. Berger, and P. Rodríguez-Bocca. 2020. “A Machine-Learning Based ConvLstm Architecture for NDVI Forecasting.” International Transactions in Operational Research 30: 2025–2048. doi:10.1111/itor.12887.
   Web of Science ®Google Scholar
• Barkhordarian, A., Saatchi, S. S., Behrangi, A., Loikith, P. C., and Mechoso, C. R. 2019. “A Recent Systematic Increase in Vapor Pressure Deficit Over Tropical South America.” Scientific Reports 9 (1): 15331.
   PubMed Web of Science ®Google Scholar
• Bentéjac, C., A. Csörg\ho, and G. Martínez-Muñoz. 2021. “A Comparative Analysis of Gradient Boosting Algorithms.” Artificial Intelligence Review 54: 1937–1967. doi:10.1007/s10462-020-09896-5.
   Web of Science ®Google Scholar
• Breiman, L. 2001. “Random Forests.” Machine Learning 45: 5–32. doi:10.1023/A:1010933404324 .
   Web of Science ®Google Scholar
• Descals, A., A. Verger, I. Filella, D. Baldocchi, I. A. Janssens, Y. H. Fu, S. Piao, M. Peaucelle, P. Ciais, and J. Peñuelas. 2020. “Soil Thawing Regulates the Spring Growth Onset in Tundra and Alpine Biomes.” The Science of the Total Environment 742: 140637. doi:10.1016/j.scitotenv.2020.140637.
   PubMed Web of Science ®Google Scholar
• Descals, A., A. Verger, G. Yin, I. Filella, Y. H. Fu, S. Piao, I. A. Janssens, and J. Peñuelas. 2022. Radiation-Constrained Boundaries Cause Nonuniform Responses of the Carbon Uptake Phenology to Climatic Warming in the Northern Hemisphere. Hoboken, New Jersey, United States: Global Change Biology.
   Google Scholar
• Descals, A., A. Verger, G. Yin, and J. Peñuelas. 2020. “A Threshold Method for Robust and Fast Estimation of Land-Surface Phenology Using Google Earth Engine.” IEEE Journal of Selected Topics in Applied Earth Observations & Remote Sensing 14: 601–606. doi:10.1109/JSTARS.2020.3039554.
   Web of Science ®Google Scholar
• Franch, B., E. F. Vermote, J.-C. Roger, E. Murphy, I. Becker-Reshef, C. Justice, M. Claverie, et al. 2017. “A 30+ Year AVHRR Land Surface Reflectance Climate Data Record and Its Application to Wheat Yield Monitoring.” Remote Sensing 9: 296. doi:10.3390/rs9030296.
   Web of Science ®Google Scholar
• Friedman, J. H. 2001. “Greedy Function Approximation: A Gradient Boosting Machine.” Annals of Statistics 29: 1189–1232. doi:10.1214/aos/1013203451.
   Web of Science ®Google Scholar
• Fu, Y., X. Li, X. Zhou, X. Geng, Y. Guo, and Y. Zhang. 2020. “Progress in Plant Phenology Modeling Under Global Climate Change.” Science China Earth Sciences 63: 1237–1247. doi:10.1007/s11430-019-9622-2.
   Web of Science ®Google Scholar
• Gensheimer, J., A. J. Turner, P. Köhler, C. Frankenberg, and J. Chen. 2022. “A Convolutional Neural Network for Spatial Downscaling of Satellite-Based Solar-Induced Chlorophyll Fluorescence (SIFnet).” Biogeosciences 19: 1777–1793. doi:10.5194/bg-19-1777-2022.
   Web of Science ®Google Scholar
• Guanter, L., I. Aben, P. Tol, J. Krijger, A. Hollstein, P. Köhler, A. Damm, J. Joiner, C. Frankenberg, and J. Landgraf. 2015. “Potential of the TROPOspheric Monitoring Instrument (TROPOMI) Onboard the Sentinel-5 Precursor for the Monitoring of Terrestrial Chlorophyll Fluorescence.” Atmospheric Measurement Techniques 8: 1337–1352. doi:10.5194/amt-8-1337-2015.
   Web of Science ®Google Scholar
• Guanter, L., C. Bacour, A. Schneider, I. Aben, T. A. van Kempen, F. Maignan, C. Retscher, et al. 2021. “The TROPOSIF Global Sun-Induced Fluorescence Dataset from the Sentinel-5P TROPOMI Mission.” Earth System Science Data 13: 5423–5440. doi:10.5194/essd-13-5423-2021.
   Web of Science ®Google Scholar
• Heskes, T., E. Sijben, I. G. Bucur, and T. Claassen. 2020. “Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Models.” Advances in Neural Information Processing Systems 33: 4778–4789.
   Google Scholar
• Johnsen, P. V., S. Riemer-Sørensen, A. T. DeWan, M. E. Cahill, and M. Langaas. 2021. “A New Method for Exploring Gene–Gene and Gene–Environment Interactions in GWAS with Tree Ensemble Methods and SHAP Values.” BMC Bioinformatics 22: 1–29. doi:10.1186/s12859-021-04041-7.
   PubMed Web of Science ®Google Scholar
• Joiner, J., Y. Yoshida, P. Köehler, P. Campbell, C. Frankenberg, C. van der Tol, P. Yang, N. Parazoo, L. Guanter, and Y. Sun. 2020. “Systematic Orbital Geometry-Dependent Variations in Satellite Solar-Induced Fluorescence (SIF) Retrievals.” Remote Sensing 12: 2346. doi:10.3390/rs12152346.
   Web of Science ®Google Scholar
• Jolly, W. M., R. Nemani, and S. W. Running. 2005. “A Generalized, Bioclimatic Index to Predict Foliar Phenology in Response to Climate.” Global Change Biology 11: 619–632. doi:10.1111/j.1365-2486.2005.00930.x.
   Web of Science ®Google Scholar
• Kandasamy, S., and R. Fernandes. 2015. “An Approach for Evaluating the Impact of Gaps and Measurement Errors on Satellite Land Surface Phenology Algorithms: Application to 20 Year NOAA AVHRR Data Over Canada.” Remote Sensing of Environment 164: 114–129. doi:10.1016/j.rse.2015.04.014.
   Web of Science ®Google Scholar
• Li, W., M. Migliavacca, M. Forkel, J. Denissen, M. Reichstein, H. Yang, G. Duveiller, U. Weber, and R. Orth. 2022. “Widespread Increasing Vegetation Sensitivity to Soil Moisture.” Nature Communications 13: 1–9. doi:10.1038/s41467-022-31667-9.
   PubMed Web of Science ®Google Scholar
• Li, X., and J. Xiao. 2019. “A Global, 0.05-Degree Product of Solar-Induced Chlorophyll Fluorescence Derived from OCO-2, MODIS, and Reanalysis Data.” Remote Sensing 11: 517. doi:10.3390/rs11050517.
   Web of Science ®Google Scholar
• Lundberg, S. M., G. Erion, H. Chen, A. DeGrave, J. M. Prutkin, B. Nair, R. Katz, J. Himmelfarb, N. Bansal, and S.-I. Lee. 2020. “From Local Explanations to Global Understanding with Explainable AI for Trees.” Nature Machine Intelligence 2: 56–67. doi:10.1038/s42256-019-0138-9.
   PubMedGoogle Scholar
• Lundberg, S. M., and S.-I. Lee. 2017. “A Unified Approach to Interpreting Model Predictions.” Advances in Neural Information Processing Systems 30: 4765–4774.
   Google Scholar
• Lundberg, S. M., B. Nair, M. S. Vavilala, M. Horibe, M. J. Eisses, T. Adams, D. E. Liston, et al. 2018. “Explainable Machine-Learning Predictions for the Prevention of Hypoxaemia During Surgery.” Nature Biomedical Engineering 2: 749–760. doi:10.1038/s41551-018-0304-0.
   PubMed Web of Science ®Google Scholar
• Meng, Y., N. Yang, Z. Qian, and G. Zhang. 2020. “What Makes an Online Review More Helpful: An Interpretation Framework Using XGBoost and SHAP Values.” Journal of Theoretical & Applied Electronic Commerce Research 16: 466–490. doi:10.3390/jtaer16030029.
   Web of Science ®Google Scholar
• Muñoz-Sabater, J., E. Dutra, A. Agustí-Panareda, C. Albergel, G. Arduini, G. Balsamo, S. Boussetta, et al. 2021. “ERA5-Land: A State-Of-The-Art Global Reanalysis Dataset for Land Applications.” Earth System Science Data Discussions 13 (9): 4349–83.
   Google Scholar
• Peñuelas, J., T. Rutishauser, and I. Filella. 2009. “Phenology Feedbacks on Climate Change.” Science 324: 887–888. doi:10.1126/science.1173004.
   PubMed Web of Science ®Google Scholar
• Piao, S., Q. Liu, A. Chen, I. A. Janssens, Y. Fu, J. Dai, L. Liu, X. Lian, M. Shen, and X. Zhu. 2019. “Plant Phenology and Global Climate Change: Current Progresses and Challenges.” Global Change Biology 25: 1922–1940. doi:10.1111/gcb.14619.
   PubMed Web of Science ®Google Scholar
• Shapley, L. S., 1953. “Stochastic Games.“ Proceedings of the National Academy of Sciences (PNAS) 39 (10): 1095–1100.
   PubMed Web of Science ®Google Scholar
• Verger, A., F. Baret, and M. Weiss. 2014. “Near Real-Time Vegetation Monitoring at Global Scale.” IEEE Journal of Selected Topics in Applied Earth Observations & Remote Sensing 7: 3473–3481. doi:10.1109/JSTARS.2014.2328632.
   Web of Science ®Google Scholar
• Wang, D., S. Thunéll, U. Lindberg, L. Jiang, J. Trygg, and M. Tysklind. 2022. “Towards Better Process Management in Wastewater Treatment Plants: Process Analytics Based on SHAP Values for Tree-Based Machine Learning Methods.” Journal of Environmental Management 301: 113941. doi:10.1016/j.jenvman.2021.113941.
   PubMed Web of Science ®Google Scholar
• Weber, U., M. Jung, M. Reichstein, C. Beer, M. Braakhekke, V. Lehsten, D. Ghent, et al. 2009. “The Interannual Variability of Africa’s Ecosystem Productivity: A Multi-Model Analysis.” Biogeosciences 6: 285–295. doi:10.5194/bg-6-285-2009.
   Web of Science ®Google Scholar
• Weiss, M., F. Baret, and A. Verger, 2014. “BELMANIP2: Enhancement of the CEOS-BELMANIP Ensemble of Sites Used for the Validation of Land Products from Medium Resolution Sensors.” Fourth International Symposium on Recent Advances in Quantitative Remote Sensing, Valencia, Spain.
   Google Scholar
• Yang, L., and A. Shami. 2020. “On Hyperparameter Optimization of Machine Learning Algorithms: Theory and Practice.” Neurocomputing 415: 295–316. doi:10.1016/j.neucom.2020.07.061.
   Web of Science ®Google Scholar
• Zhang, Y., R. Commane, S. Zhou, A. P. Williams, and P. Gentine. 2020. “Light Limitation Regulates the Response of Autumn Terrestrial Carbon Uptake to Warming.” Nature Climate Change 10: 739–743. doi:10.1038/s41558-020-0806-0.
   Web of Science ®Google Scholar
• Zhang, Y., P. Gentine, X. Luo, X. Lian, Y. Liu, S. Zhou, A. M. Michalak, et al. 2022. “Increasing Sensitivity of Dryland Vegetation Greenness to Precipitation Due to Rising Atmospheric CO2.” Nature Communications 13: 4875. doi:10.1038/s41467-022-32631-3.
   PubMed Web of Science ®Google Scholar
• Zhan, C., R. Orth, M. Migliavacca, S. Zaehle, M. Reichstein, J. Engel, A. Rammig, and A. J. Winkler. 2022. “Emergence of the Physiological Effects of Elevated CO2 on Land–Atmosphere Exchange of Carbon and Water.” Global Change Biology 28: 7313–7326. doi:10.1111/gcb.16397.
   PubMed Web of Science ®Google Scholar
• Zhou, Y., B. J. Wigley, M. F. Case, C. Coetsee, and A. C. Staver. 2020. “Rooting Depth as a Key Woody Functional Trait in Savannas.” The New Phytologist 227: 1350–1361. doi:10.1111/nph.16613.
   PubMed Web of Science ®Google Scholar