About this Research Topic
Geostatistical Learning (GL) is the specialized branch of geostatistics that is concerned with the application of statistical (machine) learning with geospatial data (Hoffimann et al. 2021). In spite of its recent appearance in the literature, the branch has gained the attention of geoscientists around the world who are aware of the limitations of non-geospatial statistical learning theory, including the lack of explicit representation of geospatial associations.
As is usually the case with geostatistics, advances in theory are achieved through practical applications in geosciences, or any field of science that studies geospatial data with statistical methods. The issues raised by these applications have not been considered before in non-geospatial machine learning (ML), and deserve further investigation for the success of geostatistical modeling in modern industries.
The aim of this Research Topic is to collect applications of geostatistical learning in different scientific fields. We welcome submissions that illustrate successes and failures of non-geospatial machine learning methodologies with geospatial data, as well as submissions that contribute to theoretical understanding of learning models in geospatial settings.
Potential applications include but are not limited to the following:
● Mining and geometallurgical modeling for energy transition
● Agriculture and crop yield modeling for sustainable food production
● Subsurface modeling for carbon capture and sequestration
● Climate, glaciological, hydrological, and environmental modeling
● Disease modeling and public health
● Water-energy-food nexus
Hoffimann J., Zortea M., de Carvalho B., Zadrozny B. Geostatistical Learning: Challenges and Opportunities. Frontiers in Applied Mathematics and Statistics (2021) DOI=10.3389/fams.2021.689393
Topic Editor Júlio Hoffimann is the founder and CEO of Arpeggeo® Technologies. The other Topic Editors declare no competing interests with regard to the Research Topic subject.
As is usually the case with geostatistics, advances in theory are achieved through practical applications in geosciences, or any field of science that studies geospatial data with statistical methods. The issues raised by these applications have not been considered before in non-geospatial machine learning (ML), and deserve further investigation for the success of geostatistical modeling in modern industries.
The aim of this Research Topic is to collect applications of geostatistical learning in different scientific fields. We welcome submissions that illustrate successes and failures of non-geospatial machine learning methodologies with geospatial data, as well as submissions that contribute to theoretical understanding of learning models in geospatial settings.
Potential applications include but are not limited to the following:
● Mining and geometallurgical modeling for energy transition
● Agriculture and crop yield modeling for sustainable food production
● Subsurface modeling for carbon capture and sequestration
● Climate, glaciological, hydrological, and environmental modeling
● Disease modeling and public health
● Water-energy-food nexus
Hoffimann J., Zortea M., de Carvalho B., Zadrozny B. Geostatistical Learning: Challenges and Opportunities. Frontiers in Applied Mathematics and Statistics (2021) DOI=10.3389/fams.2021.689393
Topic Editor Júlio Hoffimann is the founder and CEO of Arpeggeo® Technologies. The other Topic Editors declare no competing interests with regard to the Research Topic subject.
Keywords: geostatistical learning, geospatial data, applications, mining, agriculture, energy, climate, water, environment
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
