Publications

Research areas

• Machine Learning & AI — machine learning models for coffee quality, COVID-19 risk classification and health data analysis.
• Topological Data Analysis — alpha shapes, Vietoris-Rips complexes and computational homology applied to dimension reduction.
• Nonparametric Statistics — conditional covariance estimation, dimension reduction and kernel methods.
• Sensitivity Analysis — Sobol indices and nonparametric estimation of main effects and interactions.
• Actuarial Science — loss distributions, survival models, credit and operational risk.
• Geometric Goodness-of-Fit — geometric measures of goodness of fit using alpha shapes and UMAP.

Journal articles

• 2026 — Rojas-Chacón, J.A., Echeverría-Beirute, F., Jiménez Madrigal, J.P., Faggioli, V., Solís, M., & Gatica-Arias, A. Exploring the coffee fruit microbiome under different management practices and its correlation with beverage quality criteria in Costa Rica. Current Microbiology, 83(2). DOI
• 2025 — Pasquier, C., Solís, M., Vilchez, V., & Núñez-Corrales, S. Machine learning-driven COVID-19 early triage and large-scale testing strategies based on the 2021 Costa Rican Actualidades survey. Mathematics in Medical and Life Sciences, 2(1). DOI
• 2025 — Solís, M., & Pasquier, C. Relative weight analysis with residualization for detecting relevant non-linear effects. Communications in Statistics — Theory and Methods, 54(23), 7553–7568. DOI
• 2025 — Solís, M., Pasquier-Jaramillo, C., Núñez-Corrales, S., Madrigal-Redondo, G., & Gatica-Arias, A. The performance of mass testing strategies for COVID-19: a case study for Costa Rica. Revista de Biología Tropical, 73(1), e57971. DOI
• 2023 — Hernández, A.J., & Solís, M. Geometric goodness of fit measure to detect patterns in data point clouds. Computational Statistics, 38(3), 1231–1253. DOI
• 2021 — Solís, M. Non-parametric estimation of the first-order Sobol indices with bootstrap bandwidth. Communications in Statistics — Simulation and Computation, 50(9), 2497–2512. DOI
• 2020 — Loubes, J.M., Marteau, C., & Solís, M. Rates of convergence in conditional covariance matrix with nonparametric entries estimation. Communications in Statistics — Theory and Methods, 49(18), 4536–4558. DOI
• 2017 — Da Veiga, S., Loubes, J.M., & Solís, M. Efficient estimation of conditional covariance matrices for dimension reduction. Communications in Statistics — Theory and Methods, 46(9), 4403–4424. DOI

Book chapters and proceedings

• 2025 — Solís, M., & Hernández, A. UMAP projections and the survival of empty space: a geometric approach to high-dimensional data. In Data Science, Classification, and AI for Modeling Decision Making, Springer, 171–179.
• 2018 — Solís, M. Topological sensitivity analysis using R. Anales del LatinR 2018, Buenos Aires, Argentina.

Preprints and datasets

• 2024 — Pasquier, C., Solís, M., Vilchez, V., & Núñez-Corrales, S. Machine learning-driven COVID-19 early triage and large-scale testing strategies. medRxiv preprint. DOI
• 2024 — Encuesta Actualidades 2021 (dataset). figshare. DOI

Software

Three R packages, two on CRAN. See the Software page for full descriptions: spatgeom, sobolnp and residualrwa.

Funded research projects

Projects registered in SIGPRO — University of Costa Rica. Full record →

Active

• 2025–2028 — Machine learning-driven coffee quality modeling using its chemical, physical, and sensory attributes. N.º 821-C5240, CIMPA. Principal investigator.
• C6651 — Integrative genomic, transcriptomic and metabolomic analysis of flavonoid biosynthesis in Rhynchospora spp.: unraveling the tricin pathway and its modulation by LED light wavelengths. School of Biology.

Completed

• 2023–2025 — Clasificador de riesgo para individuos susceptibles a COVID-19. N.º 817-C2198, CIMPA. Principal investigator.
• 2022 — Verificación de la sensibilidad in vitro de kits comerciales de RT-LAMP para la detección del virus SARS-CoV-2. N.º 817-C0530, INIFAR. Collaborating researcher.
• 2018–2020 — Estudio de modelos aditivos para la estimación de la carga alostática a través de biomarcadores. N.º 821-B8A25, CIMPA. Principal investigator.
• 2018–2020 — Análisis de sensibilidad en modelos estadísticos con teoría topológica. N.º 821-B8221, CIMPA. Principal investigator.
• 2015–2018 — Estudio de modelos de tránsito en el Gran Área Metropolitana. N.º 821-B5A26, CIMPA. Principal investigator.
• 2014–2017 — Estimación no paramétrica de la varianza y covarianza condicional para reducción de dimensión e índices de Sobol. N.º 821-B4257, CIMPA. Principal investigator.
• 2007–2008 — Clasificación y análisis de datos: extensiones y aplicaciones de técnicas modernas. N.º A7206, CIMPA. Collaborating researcher.
• C3994 — Influence of coffee management practices on the accumulation pattern of bioactive compounds in fruits and leaves of coffee (Coffea arabica L.). School of Biology.
• B6184 — Enfermedades infecciosas en Costa Rica: modelos matemáticos. CIMPA.

Talks and seminars

• Jan. 2026 — Predicting soil biodiversity in coffee agroforestry systems: a symbolic data analysis approach with machine learning. SIMMAC 2026, University of Costa Rica, San José.
• Feb. 2025 — UMAP projections and the survival of empty space: a geometric approach to high-dimensional data. Research Days in Mathematics, Universidade de Évora, Portugal (hybrid).
• Jul. 2024 — UMAP projections and the survival of empty space: a geometric approach to high-dimensional data. 18th Conference of the International Federation of Classification Societies (IFCS), University of Costa Rica, San José. Published in the proceedings.
• Jan. 2022 — Risk classifier for COVID-19 susceptible individuals using the patient previous data. SIMMAC, University of Costa Rica, San José (virtual).
• Jan. 2021 — Uso y experiencias de R-exams para Mediación Virtual en la UCR. ConectaR 2021, University of Costa Rica, San José (virtual).
• Dec. 2020 — La forma de los datos: una breve introducción a la topología de datos. Escuela de Big Data, Centro Nacional de Alta Tecnología, San José (virtual).
• Jul. 2019 — Using the package simple features (sf) for sensitivity analysis. useR! 2019, Centre Pierre Baudis, Toulouse, France.
• Jan. 2019 — Geometrical sensitivity indices using homological constructions on manifolds. ConectaR 2019, University of Costa Rica, San José.
• Sep. 2018 — Topological sensitivity analysis with manifolds. LatinR 2018, Universidad de Palermo, Buenos Aires, Argentina. Slides
• Feb. 2018 — Nonparametric estimation of the first order Sobol indices with bootstrap bandwidth. XXI SIMMAC / III LACSC, University of Costa Rica, San José (with J.M. Loubes and C. Marteau).
• Apr. 2017 — Movilidad de personas en Costa Rica a través de redes celulares. III Foro de Ciencias, University of Costa Rica, San José.
• Dec. 2016 — Descriptive analysis of mobility within the Greater Metropolitan Area of Costa Rica using cellphone data. XIV CLAPEM, University of Costa Rica, San José. Poster.
• Jan. 2016 — Principios de estadística actuarial. 4ª Escuela de Matemática Pura y Aplicada, Universidad Nacional Autónoma de León, Nicaragua. Lecture.
• Jul. 2015 — Introducción a la estadística con aplicaciones en R. Summer course, Universidad Metropolitana, Cupey, Puerto Rico. Lecture.
• Apr. 2015 — Nonparametric estimation of a conditional covariance matrix for dimension reduction. II Foro de Ciencias, University of Costa Rica, San José.
• Jul. 2013 — Nonparametric estimation of a conditional covariance matrix for dimension reduction. 29th European Meeting of Statisticians, Bernoulli Society, Budapest, Hungary.
• Jun. 2012 — Efficient estimation of conditional covariance matrices for dimension reduction. Journées de Statistiques 2012, Société Française de Statistique, Brussels, Belgium.
• Jun. 2012 — Assimilation de données pour le trafic routier. Semaine d’Étude “Mathématiques et Entreprise”, Institut de Mathématiques de Toulouse, France.
• Feb. 2012 — Introduction to nonparametric estimation. EMALCA, University of Costa Rica, San Ramón. Mini-lecture.
• Aug. 2011 — Efficient estimation of conditional covariance matrices for dimension reduction. Coloquios de Matemática, University of Costa Rica, San José.