Minor improvements

Author: juliohm

01-geodata.qmd

@@ -258,7 +258,7 @@ other table representations.
 Other popular table representations in Julia are associated
 with specific file formats:
 
-- `CSV.File` from [CSV.jl](https://github.com/JuliaData/CSV.jl) [@Quinn2023]
+- `CSV.File` from [CSV.jl](https://github.com/JuliaData/CSV.jl)
 - `XLSX.Worksheet` from [XLSX.jl](https://github.com/felipenoris/XLSX.jl)
 - Databases from [JuliaDatabases](https://github.com/JuliaDatabases)
 

references.bib

@@ -1,14 +1,14 @@
 @article{Benzanson2017,
-    title={Julia: A fresh approach to numerical computing},
-    author={Bezanson, Jeff and Edelman, Alan and Karpinski, Stefan and Shah, Viral B},
-    journal={SIAM {R}eview},
-    volume={59},
-    number={1},
-    pages={65--98},
-    year={2017},
-    publisher={SIAM},
-    doi={10.1137/141000671},
-    url={https://epubs.siam.org/doi/10.1137/141000671}
+  title={Julia: A fresh approach to numerical computing},
+  author={Bezanson, Jeff and Edelman, Alan and Karpinski, Stefan and Shah, Viral B},
+  journal={SIAM {R}eview},
+  volume={59},
+  number={1},
+  pages={65--98},
+  year={2017},
+  publisher={SIAM},
+  doi={10.1137/141000671},
+  url={https://epubs.siam.org/doi/10.1137/141000671}
 }
 
 @book{Lauwens2018,
@@ -85,56 +85,16 @@ @article{Hoffimann2021
 }
 
 @article{Bogumil2023,
- title={DataFrames.jl: Flexible and Fast Tabular Data in Julia},
- volume={107},
- url={https://www.jstatsoft.org/index.php/jss/article/view/v107i04},
- doi={10.18637/jss.v107.i04},
- abstract={DataFrames.jl is a package written for and in the Julia language offering flexible and efficient handling of tabular data sets in memory. Thanks to Julia’s unique strengths, it provides an appealing set of features: Rich support for standard data processing tasks and excellent flexibility and efficiency for more advanced and non-standard operations. We present the fundamental design of the package and how it compares with implementations of data frames in other languages, its main features, performance, and possible extensions. We conclude with a practical illustration of typical data processing operations.},
- number={4},
- journal={Journal of Statistical Software},
- author={Bouchet-Valat, Milan and Kamiński, Bogumił},
- year={2023},
- pages={1--32}
-}
-
-@software{jacob_quinn_2023_8004128,
-  author       = {Jacob Quinn and
-                  Milan Bouchet-Valat and
-                  Nick Robinson and
-                  Bogumił Kamiński and
-                  Gem Newman and
-                  Alexey Stukalov and
-                  Curtis Vogt and
-                  cjprybol and
-                  Tim Holy and
-                  Andreas Noack and
-                  Tony Kelman and
-                  Eric Davies and
-                  ExpandingMan and
-                  Ian and
-                  Lilith Orion Hafner and
-                  Morten Piibeleht and
-                  Rory Finnegan and
-                  evalparse and
-                  Aaron Michael Silberstein and
-                  Albin Heimerson and
-                  Anthony Blaom, PhD and
-                  Benjamin Lungwitz and
-                  Bernhard König and
-                  Chris de Graaf and
-                  Corey Woodfield and
-                  David Barton and
-                  Dilum Aluthge and
-                  Elliot Saba and
-                  Felipe Noronha and
-                  kragol},
-  title        = {JuliaData/CSV.jl: v0.10.11},
-  month        = {jun},
-  year         = {2023},
-  publisher    = {Zenodo},
-  version      = {v0.10.11},
-  doi          = {10.5281/zenodo.8004128},
-  url          = {https://doi.org/10.5281/zenodo.8004128}
+  title={DataFrames.jl: Flexible and Fast Tabular Data in Julia},
+  volume={107},
+  url={https://www.jstatsoft.org/index.php/jss/article/view/v107i04},
+  doi={10.18637/jss.v107.i04},
+  abstract={DataFrames.jl is a package written for and in the Julia language offering flexible and efficient handling of tabular data sets in memory. Thanks to Julia’s unique strengths, it provides an appealing set of features: Rich support for standard data processing tasks and excellent flexibility and efficiency for more advanced and non-standard operations. We present the fundamental design of the package and how it compares with implementations of data frames in other languages, its main features, performance, and possible extensions. We conclude with a practical illustration of typical data processing operations.},
+  number={4},
+  journal={Journal of Statistical Software},
+  author={Bouchet-Valat, Milan and Kamiński, Bogumił},
+  year={2023},
+  pages={1--32}
 }
 
 @software{Koolen2023,
@@ -176,13 +136,13 @@ @software{Koolen2023
 }
 
 @inproceedings{Floriani2007,
-booktitle = {Eurographics 2007 - State of the Art Reports},
-editor = {Dieter Schmalstieg and Jiri Bittner},
-title = {{Shape Representations Based on Simplicial and Cell Complexes}},
-author = {Floriani, L. De and Hui, A.},
-year = {2007},
-publisher = {The Eurographics Association},
-DOI = {10.2312/egst.20071055}
+  booktitle = {Eurographics 2007 - State of the Art Reports},
+  editor = {Dieter Schmalstieg and Jiri Bittner},
+  title = {{Shape Representations Based on Simplicial and Cell Complexes}},
+  author = {Floriani, L. De and Hui, A.},
+  year = {2007},
+  publisher = {The Eurographics Association},
+  DOI = {10.2312/egst.20071055}
 }
 
 @article{Danisch2021,
@@ -416,18 +376,18 @@ @article{Aitchison1982
 }
 
 @article{Friedman1987,
- ISSN = {01621459},
- URL = {http://www.jstor.org/stable/2289161},
- abstract = {A new projection pursuit algorithm for exploring multivariate data is presented that has both statistical and computational advantages over previous methods. A number of practical issues concerning its application are addressed. A connection to multivariate density estimation is established, and its properties are investigated through simulation studies and application to real data. The goal of exploratory projection pursuit is to use the data to find low- (one-, two-, or three-) dimensional projections that provide the most revealing views of the full-dimensional data. With these views the human gift for pattern recognition can be applied to help discover effects that may not have been anticipated in advance. Since linear effects are directly captured by the covariance structure of the variable pairs (which are straightforward to estimate) the emphasis here is on the discovery of nonlinear effects such as clustering or other general nonlinear associations among the variables. Although arbitrary nonlinear effects are impossible to parameterize in full generality, they are easily recognized when presented in a low-dimensional visual representation of the data density. Projection pursuit assigns a numerical index to every projection that is a functional of the projected data density. The intent of this index is to capture the degree of nonlinear structuring present in the projected distribution. The pursuit consists of maximizing this index with respect to the parameters defining the projection. Since it is unlikely that there is only one interesting view of a multivariate data set, this procedure is iterated to find further revealing projections. After each maximizing projection has been found, a transformation is applied to the data that removes the structure present in the solution projection while preserving the multivariate structure that is not captured by it. The projection pursuit algorithm is then applied to these transformed data to find additional views that may yield further insight. This projection pursuit algorithm has potential advantages over other dimensionality reduction methods that are commonly used for data exploration. It focuses directly on the "interestingness" of a projection rather than indirectly through the interpoint distances. This allows it to be unaffected by the scale and (linear) correlational structure of the data, helping it to overcome the "curse of dimensionality" that tends to plague methods based on multidimensional scaling, parametric mapping, cluster analysis, and principal components.},
- author = {Jerome H. Friedman},
- journal = {Journal of the American Statistical Association},
- number = {397},
- pages = {249--266},
- publisher = {[American Statistical Association, Taylor & Francis, Ltd.]},
- title = {Exploratory Projection Pursuit},
- urldate = {2023-09-28},
- volume = {82},
- year = {1987}
+  ISSN = {01621459},
+  URL = {http://www.jstor.org/stable/2289161},
+  abstract = {A new projection pursuit algorithm for exploring multivariate data is presented that has both statistical and computational advantages over previous methods. A number of practical issues concerning its application are addressed. A connection to multivariate density estimation is established, and its properties are investigated through simulation studies and application to real data. The goal of exploratory projection pursuit is to use the data to find low- (one-, two-, or three-) dimensional projections that provide the most revealing views of the full-dimensional data. With these views the human gift for pattern recognition can be applied to help discover effects that may not have been anticipated in advance. Since linear effects are directly captured by the covariance structure of the variable pairs (which are straightforward to estimate) the emphasis here is on the discovery of nonlinear effects such as clustering or other general nonlinear associations among the variables. Although arbitrary nonlinear effects are impossible to parameterize in full generality, they are easily recognized when presented in a low-dimensional visual representation of the data density. Projection pursuit assigns a numerical index to every projection that is a functional of the projected data density. The intent of this index is to capture the degree of nonlinear structuring present in the projected distribution. The pursuit consists of maximizing this index with respect to the parameters defining the projection. Since it is unlikely that there is only one interesting view of a multivariate data set, this procedure is iterated to find further revealing projections. After each maximizing projection has been found, a transformation is applied to the data that removes the structure present in the solution projection while preserving the multivariate structure that is not captured by it. The projection pursuit algorithm is then applied to these transformed data to find additional views that may yield further insight. This projection pursuit algorithm has potential advantages over other dimensionality reduction methods that are commonly used for data exploration. It focuses directly on the "interestingness" of a projection rather than indirectly through the interpoint distances. This allows it to be unaffected by the scale and (linear) correlational structure of the data, helping it to overcome the "curse of dimensionality" that tends to plague methods based on multidimensional scaling, parametric mapping, cluster analysis, and principal components.},
+  author = {Jerome H. Friedman},
+  journal = {Journal of the American Statistical Association},
+  number = {397},
+  pages = {249--266},
+  publisher = {[American Statistical Association, Taylor & Francis, Ltd.]},
+  title = {Exploratory Projection Pursuit},
+  urldate = {2023-09-28},
+  volume = {82},
+  year = {1987}
 }
 
 @book{Devadoss2011,
@@ -463,3 +423,44 @@ @book{Cheng2012
   year = {2012},
   month = {dec},
 }
+
+@software{Moyner2025,
+  author       = {Olav Møyner and
+                  Jakob Torben and
+                  Øystein Klemetsdal and
+                  Bruno M. Pacheco and
+                  Andrés Riedemann and
+                  Grant Bruer and
+                  andreas-brostrom and
+                  Kai Bao and
+                  Richard Rex and
+                  Tim Holy and
+                  Ziyi Yin},
+  title        = {sintefmath/JutulDarcy.jl: v0.2.40},
+  month        = jan,
+  year         = 2025,
+  publisher    = {Zenodo},
+  version      = {v0.2.40},
+  doi          = {10.5281/zenodo.14671781},
+  url          = {https://doi.org/10.5281/zenodo.14671781},
+  swhid        = {swh:1:dir:50d8ba7998a9777022e264c8b0645e5131f6e551
+                   ;origin=https://doi.org/10.5281/zenodo.7775737;vis
+                   it=swh:1:snp:34dc9ee3721eb33fef740e137aaafc9aac7ba
+                   891;anchor=swh:1:rel:2ecc272caf14d187f4e9c57b76493
+                   ee8c2f57088;path=sintefmath-JutulDarcy.jl-072c6c0
+                  },
+}
+
+@article{Fouedjio2016,
+  title = {A hierarchical clustering method for multivariate geostatistical data},
+  journal = {Spatial Statistics},
+  volume = {18},
+  pages = {333-351},
+  year = {2016},
+  issn = {2211-6753},
+  doi = {https://doi.org/10.1016/j.spasta.2016.07.003},
+  url = {https://www.sciencedirect.com/science/article/pii/S2211675316300367},
+  author = {Francky Fouedjio},
+  keywords = {Clustering, Geostatistics, Non-parametric, Multivariate data, Spatial correlation, Spatial contiguity},
+  abstract = {Multivariate geostatistical data have become omnipresent in the geosciences and pose substantial analysis challenges. One of them is the grouping of data locations into spatially contiguous clusters so that data locations within the same cluster are more similar while clusters are different from each other. Spatially contiguous clusters can significantly improve the interpretation that turns the resulting clusters into meaningful geographical subregions. In this paper, we develop an agglomerative hierarchical clustering approach that takes into account the spatial dependency between observations. It relies on a dissimilarity matrix built from a non-parametric kernel estimator of the multivariate spatial dependence structure of data. It integrates existing methods to find the optimal number of clusters and to evaluate the contribution of variables to the clustering. The capability of the proposed approach to provide spatially compact, connected and meaningful clusters is assessed using multivariate synthetic and real datasets. The proposed clustering method gives satisfactory results compared to other similar geostatistical clustering methods.}
+}