update m3_dev branch (#50)

* Added etrainee_m4_utils to the python env, fixed missing figure (#43)

* Added etrainee_m4_utils

* import of our modules changed to etrainee_m4_utils

* Fixed missing fig 3

---------

Co-authored-by: jdvorak <jakub.dvorak@natur.cuni.cz>

* M4 rev (#44)

* Added etrainee_m4_utils

* import of our modules changed to etrainee_m4_utils

* Fixed missing fig 3

* Added links to citations + added our isprs annals paper from 2022

---------

Co-authored-by: jdvorak <jakub.dvorak@natur.cuni.cz>

* M4 rev - theme 2 update (#45)

* edits

* edits

* edits

* edits

* edits

* typos and equation fixes

* typos and equation fixes

* language and grammar check

* replace temporary intro file with full version

* minor fixes

* delete temp file

* minor fixes

* minor fixes

* image size adjusted

---------

Co-authored-by: jdvorak <jakub.dvorak@natur.cuni.cz>
Co-authored-by: Jakub Dvorak <jacobdvorakcz@gmail.com>

* Added new paper (#47)

* Added new paper

Added new paper (https://doi.org/10.5194/isprs-archives-XLVIII-1-W2-2023-989-2023) to citation section and replaced link to draft version.

* readme + citation edits regarding ISPRS conference paper ; deleted draft version pdf

---------

Co-authored-by: srollera <134652988+srollera@users.noreply.github.com>

* Update T1_spectral-temporal_profiles.md (#42)

added a missing parenthesis

* M3 dev (#48)

* Fix typo in machine learning part

* fix some typos in the point cloud programming part

* change back to dummy directroy path in 02 point cloud programming

---------

Co-authored-by: han16nah <han_nah@mailbox.org>

---------

Co-authored-by: Jakub Dvorak <jacobdvorakcz@gmail.com>
Co-authored-by: jdvorak <jakub.dvorak@natur.cuni.cz>
Co-authored-by: srollera <134652988+srollera@users.noreply.github.com>
Co-authored-by: vivienzahs <64486622+vivienzahs@users.noreply.github.com>
Co-authored-by: Kryndlea <131773776+Kryndlea@users.noreply.github.com>
Co-authored-by: han16nah <han_nah@mailbox.org>

CITATION.cff

@@ -85,6 +85,8 @@ references:
         given-names: L.
         orcid: "https://orcid.org/0000-0002-0270-0516"
     journal: "ISPRS Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences"
-    title: "E-TRAINEE: Open e-learning course on time series analysis in remote sensing"
+    title: "E-TRAINEE: Open E-learning course on Time Series Analysis in Remote Sensing"
     type: article
     year: 2023
+    doi: "10.5194/isprs-archives-XLVIII-1-W2-2023-989-2023"
+    url: 'https://doi.org/10.5194/isprs-archives-XLVIII-1-W2-2023-989-2023'

README.md

@@ -56,9 +56,9 @@ Please cite E-TRAINEE when using it in your teaching or training, and reference
 
 E-TRAINEE Development Team. {year} ETRAINEE - E-learning course on Time Series Analysis in Remote Sensing for Understanding Human-Environment Interactions. https://doi.org/10.5281/zenodo.8402924
 
-The development team has also presented the course here:
+The course was also presented in the form of a conference paper at the ISPRS Geospatial Week 2023:
 
-Potůčková, Albrechtová, Anders, Červená, Dvořák, Gryguc, Höfle, Hunt, Lhotáková, Marcinkowska-Ochtyra, Mayr, Neuwirthová, Ochtyra, Rutzinger, Šedová, Šrollerů, Kupková (2023): E-TRAINEE: Open E-Learning Course on Time Series Analysis in Remote Sensing , Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci. (in print) [draft version](ETrainee_ISPRS_GeoSpatialWeek_DRAFT.pdf)
+Potůčková, M., Albrechtová, J., Anders, K., Červená, L., Dvořák, J., Gryguc, K., Höfle, B., Hunt, L., Lhotáková, Z., Marcinkowska-Ochtyra, A., Mayr, A., Neuwirthová, E., Ochtyra, A., Rutzinger, M., Šedová, A., Šrollerů, A., and Kupková, L. (2023): E-TRAINEE: Open E-Learning course on Time Series Analysis in Remote Sensing. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. Vol. XLVIII-1/W2-2023, pp. 989-996. [https://doi.org/10.5194/isprs-archives-XLVIII-1-W2-2023-989-2023](https://doi.org/10.5194/isprs-archives-XLVIII-1-W2-2023-989-2023)
 
 ## License
 Except when explicitly stated otherwise, the course is licensed under the [CC BY-SA 4.0](https://creativecommons.org/licenses/by-sa/4.0/) license, associated code is licensed under the [MIT](https://choosealicense.com/licenses/mit/) license.

course/assets/python_envs/etrainee_m4.yml

@@ -252,4 +252,5 @@ dependencies:
     - networkx==3.1
     - torchnet==0.0.4
     - visdom==0.2.4
+    - etrainee_m4_utils
 

course/module1/01_principles_of_remote_sensing_time_series/T1_spectral-temporal_profiles.md

@@ -42,7 +42,7 @@ import matplotlib.pyplot as plt
 import seaborn as sns
 
 txtfiles = glob(os.path.join(
-    'T_1_point_profiles', 'profile*.txt')           # profiles in directory /T_1-1_point_profiles/
+    'T_1_point_profiles', 'profile*.txt'))           # profiles in directory /T_1-1_point_profiles/
 
 # read all point profiles (*.txt) into a dataframe and add it to a list
 df_list= []                                           # create empty list to store dataframes

course/module4/03_relating_imagery_lab_vegetation/03_02_principles_of_laboratory_spectroscopy.md

@@ -49,10 +49,10 @@ Field spectroradiometers measure reflectance at various hierarchical levels depe
 However, the reflectance measurements with CP or IS are not interchangeable. The main reason is the difference between geometry of the light source and the sensor, providing specific advantages regarding speed, laboriousness, and field operability of the spectra collection. The radiation quantity measured by the CP is usually termed in the literature as bidirectional reflectance factor (BRF) as the light source and sensor geometry is fixed in stable directional position to each other (*Figure 3A* ). The radiation quantity acquired by the IS is called directional-hemispherical reflectance factor (DHRF) for having the directional light source and having the reflected or transmitted radiation integrated from the whole hemisphere (*Figure 3B* ). There are several studies focused on the comparison of those two types of spectral quantities [Potůčková et al., 2016a](#references)), or between DHRF acquired by two types of integrating spheres ([Hovi et al., 2020](#references)).
 
 <p align="center">
-<img src="media/t03_02_fig3.jpg" title="Bidirectional and Directional-Hemispherical reflectance factors" alt="Figure 3" width="600"/>
+<img src="media/t03_02_fig3.png" title="Bidirectional and Directional-Hemispherical reflectance factors" alt="Figure 3" width="600"/>
 </p>
 
-*Figure 3. Two most commonly measured reflectance quantities A) Bidirectional Reflectance Factor by the contact probe or leaf clip and B) Directional-Hemispherical reflectance factor by the integrating sphere. (Figure modified from [Schaepman-Strub et al. 2006](https://doi.org/10.1016/j.rse.2006.03.002) / [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/))*
+*Figure 3. Two most commonly measured reflectance quantities A) Bidirectional Reflectance Factor by the contact probe or leaf clip and B) Directional-Hemispherical reflectance factor by the integrating sphere. (Figure by the authors).*
 
 
 ## Spectral reflectance acquisition with the spectroradiometer ASD FieldSpec®

course/module4/04_time_series_specifics/04_exercise_cnn_1d.ipynb

@@ -70,9 +70,9 @@
     "- __os.path__ - Path manipulation\n",
     "- __tqdm__ - show progress bars during training\n",
     "\n",
-    "- __image_preprocessing__ - Our library holding functions for image tiling, preprocessing, etc.\n",
-    "- __inference_utils__ - Our library for correctly exporting classifed images\n",
-    "- __visualisation_utils__ - Our library for visualising the data\n",
+    "- __etrainee_m4_utils.image_preprocessing__ - Our library holding functions for image tiling, preprocessing, etc.\n",
+    "- __etrainee_m4_utils.inference_utils__ - Our library for correctly exporting classifed images\n",
+    "- __etrainee_m4_utils.visualisation_utils__ - Our library for visualising the data\n",
     "\n",
     "Two external libraries are not imported directly in this notebook, but are used by functions in _image_preprocessing_ and _inference_utils_:\n",
     "\n",
@@ -102,9 +102,9 @@
     "from sklearn.model_selection import KFold, StratifiedKFold, train_test_split\n",
     "from sklearn.metrics import classification_report\n",
     "\n",
-    "import image_preprocessing\n",
-    "import inference_utils\n",
-    "import visualisation_utils\n",
+    "from etrainee_m4_utils import image_preprocessing\n",
+    "from etrainee_m4_utils import inference_utils\n",
+    "from etrainee_m4_utils import visualisation_utils\n",
     "\n",
     "# GLOBAL SETTINGS\n",
     "plt.rcParams['figure.figsize'] = [4, 4]\n",

course/module4/04_time_series_specifics/04_exercise_cnn_2d.ipynb

@@ -66,9 +66,9 @@
     "- __os.path__ - Path manipulation\n",
     "- __tqdm__ - show progress bars during training\n",
     "\n",
-    "- __image_preprocessing__ - Our library holding functions for image tiling, preprocessing, etc.\n",
-    "- __inference_utils__ - Our library for correctly exporting classifed images\n",
-    "- __visualisation_utils__ - Our library for visualising the data\n",
+    "- __etrainee_m4_utils.image_preprocessing__ - Our library holding functions for image tiling, preprocessing, etc.\n",
+    "- __etrainee_m4_utils.inference_utils__ - Our library for correctly exporting classifed images\n",
+    "- __etrainee_m4_utils.visualisation_utils__ - Our library for visualising the data\n",
     "\n",
     "Two external libraries are not imported directly in this notebook, but are used by functions in _image_preprocessing_ and _inference_utils_:\n",
     "\n",
@@ -97,9 +97,9 @@
     "from sklearn.metrics import classification_report\n",
     "from sklearn.model_selection import KFold, StratifiedKFold, train_test_split\n",
     "\n",
-    "import image_preprocessing\n",
-    "import inference_utils\n",
-    "import visualisation_utils\n",
+    "from etrainee_m4_utils import image_preprocessing\n",
+    "from etrainee_m4_utils import inference_utils\n",
+    "from etrainee_m4_utils import visualisation_utils\n",
     "\n",
     "# GLOBAL SETTINGS\n",
     "plt.rcParams['figure.figsize'] = [5, 5]\n",