An integrated view of complex landscapes: A big data-model integration approach to transdisciplinary science

Authors: Peters, Debra; BURRUSS, N. DYLAN - New Mexico State University; Rodriguez, Luis; McVey, David; Elias, Emile; PELZEL-MCCLUSKEY, ANGELA - Animal And Plant Health Inspection Service (APHIS); Derner, Justin; Schrader, Theodore - Scott; YAO, JIN - Non ARS Employee; Pauszek, Steven; LOMBARD, JASON - Animal And Plant Health Inspection Service (APHIS); ARCHER, STEVEN - University Of Arizona; Bestelmeyer, Brandon; Browning, Dawn; BRUNGARD, COLBY - New Mexico State University; Hatfield, Jerry; HANAN, NIALL - New Mexico State University; Herrick, Jeffrey - Jeff; OKIN, GREGORY - University Of California; SALA, OSVALDO - Arizona State University; SAVOY, HEATHER - New Mexico State University; VIVONI, ENRIQUE - Arizona State University

Submitted to: Bioscience
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 5/16/2018
Publication Date: 9/1/2018
Citation: Peters, D.C., Burruss, N., Rodriguez, L.L., McVey, D.S., Elias, E.H., Pelzel-McCluskey, A.M., Derner, J.D., Schrader, T.S., Yao, J., Pauszek, S.J., Lombard, J., Archer, S.R., Bestelmeyer, B.T., Browning, D.M., Brungard, C., Hatfield, J.L., Hanan, N.P., Herrick, J.E., Okin, G.S., Sala, O.E., Savoy, H., Vivoni, E.R. 2018. An integrated view of complex landscapes: A big data-model integration approach to transdisciplinary science. Bioscience. 68:653-669. https://doi.org/10.1093/biosci/biy069.
DOI: https://doi.org/10.1093/biosci/biy069

Interpretive Summary: We developed a Trans-Disciplinary Data-Model Integration (TDMI) approach that focuses on spatio-temporal modeling and cross-scale interactions, and employs human-centered machine learning strategies in order to assist in understanding, predicting, and managing for complex dynamics in agricultural systems. Our approach integrates knowledge and data on: (1) biological processes, (2) spatial heterogeneity in the land surface template, and (3) variability in environmental drivers using data and knowledge drawn from multiple lines of evidence (i.e., observations, experimental manipulations, analytical and numerical models, products from imagery, conceptual model reasoning, theory). We apply this approach to a suite of increasingly complex agricultural and ecologically-relevant problems. We then provide a framework linked with a Data Science Integration System (DSIS) to allow other questions to be addressed in the future.

Technical Abstract: The Earth is a complex system comprised of many interacting spatial and temporal scales. Understanding, predicting, and managing for these dynamics requires a trans-disciplinary integrated approach. Although there have been calls for this integration, a general approach is needed. We developed a Trans-Disciplinary Data-Model Integration (TDMI) approach that focuses on spatio-temporal modeling and cross-scale interactions, and employs human-centered machine learning strategies. Applied to ecological problems, our approach integrates knowledge and data on: (1) biological processes, (2) spatial heterogeneity in the land surface template, and (3) variability in environmental drivers using data and knowledge drawn from multiple lines of evidence (i.e., observations, experimental manipulations, analytical and numerical models, products from imagery, conceptual model reasoning, theory). We apply this approach to a suite of increasingly complex ecologically-relevant problems. We then provide a framework linked with a Data Science Integration System (DSIS) to allow other questions to be addressed in the future.