Santos, Fabián
Thumbnail Image
Preferred name
Santos, Fabián
Main Affiliation
Quito
Email
ernestosantos@uti.edu.ec
ORCID
Scopus Author ID
57193085558

Research Output

Filters

7
Reset filters

Settings
Now showing 1 - 7 of 7
No Thumbnail Available
Publication

Leveraging Geographic Research, Web Applications and Surveys in the Construction of Educational Strategies in Ecuador

2024 , Santos, Fabián , Fernanda Suárez , Joaquín Gairín

Communicating geographic research and contributing to the construction of regional educational strategies represent little-explored challenges. This paper takes a geographic research study that discusses territorial imbalances in access to higher education in Ecuador as an example. It describes a methodology based on developing a web application software (WAS) named “Brechas Educativas”. This software aims to disseminate research results and encourages users to reflect on their territories and the access to higher education for their student populations. Subsequently, we collected perceptions about the WAS, factors affecting academic performance and the assimilation of experiences post-COVID-19 pandemic through a survey. To achieve this, virtual workshops were conducted with 95 educational institutions (EIs) across Ecuador, complemented by email correspondence with a group of 3284 EIs. Our results enabled us to understand the good practices for developing WAS for scientific dissemination, the achievements and pitfalls in collecting opinions from the EIs and to draft focused strategies for educational decision-making in this area, informed by both app traffic and survey responses.

View
No Thumbnail Available
Publication

An Approach Based on Web Scraping and Denoising Encoders to Curate Food Security Datasets

2023 , Santos, Fabián , Acosta N.

Ensuring food security requires the publication of data in a timely manner, but often this information is not properly documented and evaluated. Therefore, the combination of databases from multiple sources is a common practice to curate the data and corroborate the results; however, this also results in incomplete cases. These tasks are often labor-intensive since they require a case-wise review to obtain the requested and completed information. To address these problems, an approach based on Selenium web-scraping software and the multiple imputation denoising autoencoders (MIDAS) algorithm is presented for a case study in Ecuador. The objective was to produce a multidimensional database, free of data gaps, with 72 species of food crops based on the data from 3 different open data web databases. This methodology resulted in an analysis-ready dataset with 43 parameters describing plant traits, nutritional composition, and planted areas of food crops, whose imputed data obtained an R-square of 0.84 for a control numerical parameter selected for validation. This enriched dataset was later clustered with K-means to report unprecedented insights into food crops cultivated in Ecuador. The methodology is useful for users who need to collect and curate data from different sources in a semi-automatic fashion. © 2023 by the authors.

View
No Thumbnail Available
Publication

Strengthening the Adoption of Copernicus Services in Latin America: Capacity Building Experiences in Ecuador and Bolivia

2025 , Santos, Fabián , Luisa Di Lucchio , Manuel Múgica Barrera

The Copernicus program, an initiative by the European Union, offers open-access Earth observation data and high-level products through its services. However, these services are less well known in Latin America, underscoring the need to strengthen capacity-building efforts. In this context, this research examines the design and implementation of training workshops in Ecuador and panel discussions in Bolivia, focusing on the role of Copernicus Services in addressing regional challenges related to Environmental, Food Security, Climate Change, Security, and Risk Management through geospatial technologies. By tailoring training sessions in Ecuador to enhance stakeholders’ capabilities and conducting panel discussions in Bolivia to promote these services among public entities, this research highlights the successes and challenges of these initiatives. We emphasize the importance of flexible event design, alignment with local contexts, and the integration of interactive methodologies to enhance stakeholder engagement and learning outcomes. Additionally, differences and similarities between the event formats are discussed in terms of purposes and objectives, audience engagement, content delivery, attendance, and post-event outcomes. Finally, we outline the convergences and divergences in strategic priorities for future Copernicus Services training initiatives in both countries.

View
No Thumbnail Available
Publication

The socioeconomic drivers of invasive plant cover in rural Galapagos

2025 , Nicole Acosta-Vásconez , Heinke Jäger , Uwe A. Schneider , Santos, Fabián , Khondokar H. Kabir , Kerstin Jantke

The unique biodiversity of the Galapagos Islands faces a significant threat from invasive plants, particularly in the highlands. Invasive plant occurrence is expected to shift in response to changing rural socioeconomic factors, further exacerbating the threat to native ecosystems. So far, limited research has integrated socioeconomic factors as drivers of invasive plant cover changes across the rural landscape. Our study employed stakeholder surveys, plant cover models, and spatial and statistical analyses to identify socioeconomic factors impacting the cover of commonly used or controlled invasive plant species (guava, Cuban cedar, blackberry) in the rural areas of Santa Cruz and San Cristobal Islands. Relevant socioeconomic factors were selected through a ranked predictor analysis in species cover models using random forest algorithms. Both biophysical and socioeconomic predictors were included to increase model comprehensiveness. We found that biophysical factors—such as climate, soil properties, and topography—were strong predictors of Cuban cedar cover. In contrast, socioeconomic factors, soil properties, and climate were better predictors of guava. Statistical analyses revealed that landowners’ primary income source and land use had a significant influence on guava cover. Farms dependent on agriculture had lower guava cover, while those focusing on tourism had the highest. The quality of available data limited results for blackberry. Our study highlights relevant factors that should be considered for invasive plant management in rural Galapagos. It quantifies the effect of key socioeconomic variables on guava cover on Santa Cruz and San Cristobal Islands

View
No Thumbnail Available
Publication

Assessing Annual and Monthly Precipitation Anomalies in Ecuador Bioregions Using WorldClim CMIP6 GCM Ensemble Projections and Dynamic Time Warping

2025 , Santos, Fabián , José Jara , Nicole Acosta , Raúl Galeas , Bert de Bièvre

ABSTRACT The Coupled Model Inter‐comparison Project phase 6 (CMIP6) provides a suite of general circulation models (GCMs) and Socioeconomic Shared Pathways (SSPs) primarily for continental‐scale climate assessments. However, adapting these models for sub‐national assessments, particularly in countries with varied geography like Ecuador, and for complex variables such as precipitation, introduces challenges, including uncertainties in selecting appropriate GCMs and SSPs. To address these issues, we adopt a biogeographical approach that integrates regional climatic variations. Our analysis explores 26 GCMs, four SSP scenarios and four 20‐year time frames from WorldClim to evaluate discrepancies between the GCM precipitation projections, historical data and national climate projections across five Ecuadorian bioregions. This approach enabled us to sort the GCMs by annual precipitation medians, classify their monthly precipitation using Dynamic Time Warping (DTW) clustering, and develop ensembles highlighting both the largest and average precipitation anomalies within and beyond the bioregions. Among the 26 models examined, 16 projected an increase in annual precipitation in Ecuador, especially during the wet seasons, with the BCC‐CSM2‐MR model showing peak values, notably in the Choco region and eastern Amazon basin. Conversely, 10 models, with CMCC‐ESM2 showing the largest decreases, projected reduced precipitation across almost all Ecuadorian territories, except the Choco region. The largest reductions were in the Amazon basin, raising concerns about reduced precipitation. Discrepancies, primarily in the Andes and Galapagos bioregions, reveal the challenges posed by their complex topography and insular environments. While the GCMs captured spatial patterns of ENSO, our research was constrained to 20‐year averages, making direct comparison with historical records infeasible, highlighting the need for further research with shorter time frames and finer spatial resolutions. The variability in precipitation was linked to geographical factors, GCM configurations and unexpected SSP outcomes. Therefore, selecting GCMs and climatic indices tailored to specific bioregions is recommended for effective climate change impact assessments.

View
No Thumbnail Available
Publication

Impact of heavy metals on community farming activities in the central peruvian andes

2019 , Quispe-Zuniga M.R. , Santos, Fabián , Callo-Concha D. , Greve K.

The high mining potential of the Peruvian Andes has promoted booming foreign investments. The mining activity takes place on campesino community lands and headwaters. Once the government awards a mining concession, mining companies must regularly negotiate land rent with communities over the whole duration of the mining operation, often leading to disagreements. Our research objective is to identify the mining impacts on the farming activities of campesino communities in the Junin region, central Peruvian Andes. Using a mixed-methods approach involving in-depth interviews, water and soil analysis, land-cover classification and participatory mapping, we analyzed the mining-community agreements and the mining impacts on the farming lands. We arrived at two primary conclusions. First, mining activities in terms of heavy metal concentrations impact on farming lands, although the contribution of previous and concurrent activities cannot be distinguished. Second, the diverging and short-termed interests of the involved parties which circumscribe the agreements may potentially lead to conflicts. © 2019 by the authors. Licensee MDPI, Basel, Switzerland.

View
No Thumbnail Available
Publication

A geographically weighted random forest approach for evaluate forest change drivers in the Northern Ecuadorian Amazon

2019 , Santos, Fabián , Graw V. , Bonilla S.

The Tropical Andes region includes biodiversity hotspots of high conservation priority whose management strategies depend on the analysis of forest dynamics drivers (FDDs). These depend on complex social and ecological interactions that manifest on different space–time scales and are commonly evaluated through regression analysis of multivariate datasets. However, processing such datasets is challenging, especially when time series are used and inconsistencies in data collection complicate their integration. Moreover, regression analysis in FDD characterization has been criticized for failing to capture spatial variability; therefore, alternatives such as geographically weighted regression (GWR) have been proposed, but their sensitivity to multicollinearity has not yet been solved. In this scenario, we present an innovative methodology that combines techniques to: 1) derive remote sensing time series products; 2) improve census processing with dasymetric mapping; 3) combine GWR and random forest (RF) to derive local variables importance; and 4) report results based in a clustering and hypothesis testing. We applied this methodology in the northwestern Ecuadorian Amazon, a highly heterogeneous region characterized by different active fronts of deforestation and reforestation, within the time period 2000–2010. Our objective was to identify linkages between these processes and validate the potential of the proposed methodology. Our findings indicate that land-use intensity proxies can be extracted from remote sensing time series, while intercensal analysis can be facilitated by calculating population density maps. Moreover, our implementation of GWR with RF achieved accurate predictions above the 74% using the out-of-bag samples, demonstrating that derived RF features can be used to construct hypothesis and discuss forest change drivers with more detailed information. In the other hand, our analysis revealed contrasting effects between deforestation and reforestation for variables related to suitability to agriculture and accessibility to its facilities, which is also reflected according patch size, land cover and population dynamics patterns. This approach demonstrates the benefits of integrating remote sensing–derived products and socioeconomic data to understand coupled socioecological systems more from a local than a global scale. © 2019 Santos et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

View