Mapping the Groundwater Level and Soil Moisture of a Montane Peat Bog Using UAV Monitoring and Machine Learning
One of the best preconditions for the sufficient monitoring of peat bog ecosystems is the collection, processing, and analysis of unique spatial data to understand peat bog dynamics. Over two seasons, we sampled groundwater level (GWL) and soil moisture (SM) ground truth data at two diverse location...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-02-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/5/907 |
| _version_ | 1827605058907275264 |
|---|---|
| author | Theodora Lendzioch Jakub Langhammer Lukáš Vlček Robert Minařík |
| author_facet | Theodora Lendzioch Jakub Langhammer Lukáš Vlček Robert Minařík |
| author_sort | Theodora Lendzioch |
| collection | DOAJ |
| description | One of the best preconditions for the sufficient monitoring of peat bog ecosystems is the collection, processing, and analysis of unique spatial data to understand peat bog dynamics. Over two seasons, we sampled groundwater level (GWL) and soil moisture (SM) ground truth data at two diverse locations at the Rokytka Peat bog within the Sumava Mountains, Czechia. These data served as reference data and were modeled with a suite of potential variables derived from digital surface models (DSMs) and RGB, multispectral, and thermal orthoimages reflecting topomorphometry, vegetation, and surface temperature information generated from drone mapping. We used 34 predictors to feed the random forest (RF) algorithm. The predictor selection, hyperparameter tuning, and performance assessment were performed with the target-oriented leave-location-out (LLO) spatial cross-validation (CV) strategy combined with forward feature selection (FFS) to avoid overfitting and to predict on unknown locations. The spatial CV performance statistics showed low (R<sup>2</sup> = 0.12) to high (R<sup>2</sup> = 0.78) model predictions. The predictor importance was used for model interpretation, where temperature had strong impact on GWL and SM, and we found significant contributions of other predictors, such as Normalized Difference Vegetation Index (NDVI), Normalized Difference Index (NDI), Enhanced Red-Green-Blue Vegetation Index (ERGBVE), Shape Index (SHP), Green Leaf Index (GLI), Brightness Index (BI), Coloration Index (CI), Redness Index (RI), Primary Colours Hue Index (HI), Overall Hue Index (HUE), SAGA Wetness Index (TWI), Plan Curvature (PlnCurv), Topographic Position Index (TPI), and Vector Ruggedness Measure (VRM). Additionally, we estimated the area of applicability (AOA) by presenting maps where the prediction model yielded high-quality results and where predictions were highly uncertain because machine learning (ML) models make predictions far beyond sampling locations without sampling data with no knowledge about these environments. The AOA method is well suited and unique for planning and decision-making about the best sampling strategy, most notably with limited data. |
| first_indexed | 2024-03-09T06:13:24Z |
| format | Article |
| id | doaj.art-1ab3a96d5ef7492493289ca641ee11b1 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T06:13:24Z |
| publishDate | 2021-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-1ab3a96d5ef7492493289ca641ee11b12023-12-03T11:55:57ZengMDPI AGRemote Sensing2072-42922021-02-0113590710.3390/rs13050907Mapping the Groundwater Level and Soil Moisture of a Montane Peat Bog Using UAV Monitoring and Machine LearningTheodora Lendzioch0Jakub Langhammer1Lukáš Vlček2Robert Minařík3Department of Physical geography and Geoecology, Faculty of Science, Charles University, Albertov 6, 128 43 Prague 2, Czech RepublicDepartment of Physical geography and Geoecology, Faculty of Science, Charles University, Albertov 6, 128 43 Prague 2, Czech RepublicDepartment of Water Resources, Institute of Hydrodynamics, Czech Academy of Sciences, Pod Pat’ankou 30, 166 12, Prague 6, Czech RepublicDepartment of Physical geography and Geoecology, Faculty of Science, Charles University, Albertov 6, 128 43 Prague 2, Czech RepublicOne of the best preconditions for the sufficient monitoring of peat bog ecosystems is the collection, processing, and analysis of unique spatial data to understand peat bog dynamics. Over two seasons, we sampled groundwater level (GWL) and soil moisture (SM) ground truth data at two diverse locations at the Rokytka Peat bog within the Sumava Mountains, Czechia. These data served as reference data and were modeled with a suite of potential variables derived from digital surface models (DSMs) and RGB, multispectral, and thermal orthoimages reflecting topomorphometry, vegetation, and surface temperature information generated from drone mapping. We used 34 predictors to feed the random forest (RF) algorithm. The predictor selection, hyperparameter tuning, and performance assessment were performed with the target-oriented leave-location-out (LLO) spatial cross-validation (CV) strategy combined with forward feature selection (FFS) to avoid overfitting and to predict on unknown locations. The spatial CV performance statistics showed low (R<sup>2</sup> = 0.12) to high (R<sup>2</sup> = 0.78) model predictions. The predictor importance was used for model interpretation, where temperature had strong impact on GWL and SM, and we found significant contributions of other predictors, such as Normalized Difference Vegetation Index (NDVI), Normalized Difference Index (NDI), Enhanced Red-Green-Blue Vegetation Index (ERGBVE), Shape Index (SHP), Green Leaf Index (GLI), Brightness Index (BI), Coloration Index (CI), Redness Index (RI), Primary Colours Hue Index (HI), Overall Hue Index (HUE), SAGA Wetness Index (TWI), Plan Curvature (PlnCurv), Topographic Position Index (TPI), and Vector Ruggedness Measure (VRM). Additionally, we estimated the area of applicability (AOA) by presenting maps where the prediction model yielded high-quality results and where predictions were highly uncertain because machine learning (ML) models make predictions far beyond sampling locations without sampling data with no knowledge about these environments. The AOA method is well suited and unique for planning and decision-making about the best sampling strategy, most notably with limited data.https://www.mdpi.com/2072-4292/13/5/907peat bogsoil moistureUAVmachine learning (ML)random forest (RF)modelling |
| spellingShingle | Theodora Lendzioch Jakub Langhammer Lukáš Vlček Robert Minařík Mapping the Groundwater Level and Soil Moisture of a Montane Peat Bog Using UAV Monitoring and Machine Learning Remote Sensing peat bog soil moisture UAV machine learning (ML) random forest (RF) modelling |
| title | Mapping the Groundwater Level and Soil Moisture of a Montane Peat Bog Using UAV Monitoring and Machine Learning |
| title_full | Mapping the Groundwater Level and Soil Moisture of a Montane Peat Bog Using UAV Monitoring and Machine Learning |
| title_fullStr | Mapping the Groundwater Level and Soil Moisture of a Montane Peat Bog Using UAV Monitoring and Machine Learning |
| title_full_unstemmed | Mapping the Groundwater Level and Soil Moisture of a Montane Peat Bog Using UAV Monitoring and Machine Learning |
| title_short | Mapping the Groundwater Level and Soil Moisture of a Montane Peat Bog Using UAV Monitoring and Machine Learning |
| title_sort | mapping the groundwater level and soil moisture of a montane peat bog using uav monitoring and machine learning |
| topic | peat bog soil moisture UAV machine learning (ML) random forest (RF) modelling |
| url | https://www.mdpi.com/2072-4292/13/5/907 |
| work_keys_str_mv | AT theodoralendzioch mappingthegroundwaterlevelandsoilmoistureofamontanepeatbogusinguavmonitoringandmachinelearning AT jakublanghammer mappingthegroundwaterlevelandsoilmoistureofamontanepeatbogusinguavmonitoringandmachinelearning AT lukasvlcek mappingthegroundwaterlevelandsoilmoistureofamontanepeatbogusinguavmonitoringandmachinelearning AT robertminarik mappingthegroundwaterlevelandsoilmoistureofamontanepeatbogusinguavmonitoringandmachinelearning |