scholarly journals Mapping the Groundwater Level and Soil Moisture of a Montane Peat Bog Using UAV Monitoring and Machine Learning

2021 ◽  
Vol 13 (5) ◽  
pp. 907
Author(s):  
Theodora Lendzioch ◽  
Jakub Langhammer ◽  
Lukáš Vlček ◽  
Robert Minařík
Keyword(s):  
Machine Learning ◽  
Soil Moisture ◽  
Spatial Data ◽  
Groundwater Level ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Sampling Strategy ◽  
Peat Bog ◽  
Strong Impact ◽  
Ground Truth Data

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 (R2 = 0.12) to high (R2 = 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.

Mapping the groundwater level and soil moisture of a montane peat bog using UAV monitoring and machine learning

2021 ◽  
Author(s):  
Theodora Lendzioch ◽  
Jakub Langhammer ◽  
Lukas Vlcek ◽  
Robert Minarik
Keyword(s):  
Machine Learning ◽  
Soil Moisture ◽  
Spatial Data ◽  
Groundwater Level ◽  
Vegetation Index ◽  
Sampling Strategy ◽  
Ground Truth ◽  
Peat Bog ◽  
Ground Truth Data ◽  
Normalized Difference Index

<p>One of the best preconditions for sufficient monitoring of peat bog ecosystems requires a unique collection, processing, and analysis of 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), RGB-, multispectral-, and thermal orthoimages, reflecting topo-morphometry, vegetation, and surface temperature information, generated from drone mapping. We applied 34 predictors to feed the Random forest (RF) algorithm. Predictors selection, hyperparameter tuning, and performance assessment were accompanied using Leave-Location-Out (LLO) spatial Cross-Validation (CV) joined with the forward feature selection (FFS) to overcome overfitting. The spatial CV performance statistics unveiled low (R2 = 0.12) to high (R2 = 0.78) model predictions. Predictor importance was used for model interpretation, where the temperature has proved the be a powerful impact on GWL and SM and significant other predictors' contributions such as Normalized Difference 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 was certainly applied and where the predictions were highly uncertain because machine learning (ML) models make predictions far beyond sampling locations without sampling data and having no knowledge about these environments. The AOA method is perfectly suited and unique for decision-making about the best sampling strategy, notably for limited data to circumvent this issue. </p>

Estimating Regional Soil Moisture with Synergistic Use of AMSR2 and MODIS Images

2021 ◽  
Vol 87 (9) ◽  
pp. 649-660
Author(s):  
Majid Rahimzadegan ◽  
Arash Davari ◽  
Ali Sayadi
Keyword(s):  
Soil Moisture ◽  
Land Surface ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Regional Scale ◽  
Ground Truth ◽  
Absolute Error ◽  
Simple Method ◽  
Ground Truth Data ◽  
Pi Index

Soil moisture content (SMC), product of Advanced Microwave Scanning Radiometer 2 (AMSR2), is not at an adequate level of accuracy on a regional scale. The aim of this study is to introduce a simple method to estimate SMC while synergistically using AMSR2 and Moderate Resolution Imaging Spectroradiometer (MODIS) measurements with a higher accuracy on a regional scale. Two MODIS products, including daily reflectance (MYD021) and nighttime land surface temperature (LST) products were used. In 2015, 1442 in situ SMC measurements from six stations in Iran were used as ground-truth data. Twenty models were evaluated using combinations of polarization index (PI), index of soil wetness (ISW), normalized difference vegetation index (NDVI), and LST. The model revealed the best results using a quadratic combination of PI and ISW, a linear form of LST, and a constant value. The overall correlation coefficient, root-mean-square error, and mean absolute error were 0.59, 4.62%, and 3.01%, respectively.

scholarly journals Geospatial Approach for the Analysis of Forest Cover Change Detection using Machine Learning

2020 ◽  
Vol 5 (3) ◽  
pp. 335
Author(s):  
R. Sanjeeva Reddy ◽  
G. Anjan Babu ◽  
A. Rama Mohan Reddy
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Support Vector Machine ◽  
Change Detection ◽  
Spatial Data ◽  
Vegetation Index ◽  
Forest Cover ◽  
Normalized Difference Vegetation Index ◽  
Support Vector ◽  
Forest Cover Change

Spatial data classification is famous over recent years in order to extract knowledge and insights into the data. It occurs because vast experimentation was used with various classifiers, and significant improvement was examined in accuracy and performance. This study aimed to analyze forest cover change detection using machine learning. Supervised and unsupervised learning methods were used to analyze spatial data. A Vector machine was used to support the supervised learning, and a neural network method was used to support unsupervised learning. The Normalized Difference Vegetation Index (NDVI) was used to identify the bands and extract pixel information relevant to the vegetation. The supervised method shows better results because of its robust performance and better analysis of spatial data classification using vegetation index. The proposed system experimentation was implemented by analyzing the results obtained from Support Vector Machine (SVM) and NN (Neural Network) methods. It is demonstrated in the results that the use of NDVI mainly enhances the performance and increases the classifier's accuracy to a greater extent. Keywords: Spatial data; Normalized Difference Vegetation Index; NDVI;Vegetation index, Support Vector Machine; Neural Network; Forest Cover Change Copyright (c) 2020 Geosfera Indonesia Journal and Department of Geography Education, University of Jember This work is licensed under a Creative Commons Attribution-Share A like 4.0 International License

Beyond Cloud: A Fused Optic and SAR Based Solution to Monitor Crop Health

2021 ◽  
Author(s):  
Brianna Pagán ◽  
Adekunle Ajayi ◽  
Mamadou Krouma ◽  
Jyotsna Budideti ◽  
Omar Tafsi
Keyword(s):  
Machine Learning ◽  
Satellite Imagery ◽  
Cloud Cover ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Learning Approaches ◽  
Area Index ◽  
Spatial And Temporal Scales ◽  
Field Level ◽  
Crop Health

<p>The value of satellite imagery to monitor crop health in near-real time continues to exponentially grow as more missions are launched making data available at higher spatial and temporal scales. Yet cloud cover remains an issue for utilizing vegetation indexes (VIs) solely based on optic imagery, especially in certain regions and climates. Previous research has proven the ability to reconstruct VIs like the Normalized Difference Vegetation Index (NDVI) and Leaf Area Index (LAI) by leveraging synthetic aperture radar (SAR) datasets, which are not inhibited by cloud cover. Publicly available data from SAR missions like Sentinel-1 at relatively decent spatial resolutions present the opportunity for more affordable options for agriculture users to integrate satellite imagery in their day to day operations. Previous research has successfully reconstructed optic VIs (i.e. from Sentinel-2) with SAR data (i.e. from Sentinel-1) leveraging various machine learning approaches for a limited number of crop types. However, these efforts normally train on individual pixels rather than leveraging information at a field level. </p><p>Here we present Beyond Cloud, a product which is the first to leverage computer vision and machine learning approaches in order to provide fused optic and SAR based crop health information. Field level learning is especially well-suited for inherently noisy SAR datasets. Several use cases are presented over agriculture fields located throughout the United Kingdom, France and Belgium, where cloud cover limits optic based solutions to as little as 2-3 images per growing season. Preliminary efforts for additional features to the product including automated crop and soil type detection are also discussed. Beyond Cloud can be accessed via a simple API which makes integration of the results easy for existing dashboards and smart-ag tools. Overall, these efforts promote the accessibility of satellite imagery for real agriculture end users.</p><p> </p>

Characterizing waste disposal sites by using multi-spectral satellite imagery

2021 ◽  
Author(s):  
Gaetana Ganci ◽  
Annalisa Cappello ◽  
Giuseppe Bilotta ◽  
Giuseppe Pollicino ◽  
Luigi Lodato
Keyword(s):  
Soil Moisture ◽  
Surface Temperature ◽  
Waste Disposal ◽  
Land Surface ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
The State ◽  
Dump Site ◽  
Temperature State ◽  
Surrounding Areas

<p>The application of remote sensing for monitoring, detecting and analysing the spatial and extents and temporal changes of waste dumping sites and landfills could become a cost-effective and powerful solution. Multi-spectral satellite images, especially in the thermal infrared, can be exploited to characterize the state of activity of a landfill.  Indeed, waste disposal sites, during the period of activity, can show differences in surface temperature (LST, Land Surface Temperature), state of vegetation (estimated through NDVI, Normalized Difference Vegetation Index) or soil moisture (estimated through NDWI, Normalized Difference Water Index) compared to neighboring areas. Landfills with organic waste typically show higher temperatures than surrounding areas due to exothermic decomposition activities. In fact, the biogas, in the absence or in case of inefficiency of the conveying plants, rises through the layers of organic matter and earth (landfill body) until it reaches the surface at a temperature of over 40 ° C. Moreover, in some cases, leachate contamination of the aquifers can be identified by analyzing the soil moisture, through the estimate of the NDWI, and the state of suffering of the vegetation surrounding the site, through the estimate of the NDVI. This latter can also be an indicator of soil contamination due to the presence of toxic and potentially dangerous waste when buried or present nearby. To take into account these facts, we combine the LST, NDVI and NDWI indices of the dump site and surrounding areas in order to characterize waste disposal sites. Preliminary results show how this approach can bring out the area and level of activity of known landfill sites. This could prove particularly useful for the definition of intervention priorities in landfill remediation works.</p>

scholarly journals A new method for estimating of evapotranspiration and surface soil moisture from optical and thermal infrared measurements: the simplified triangle

2020 ◽  
Author(s):  
Toby N. Carlson ◽  
George Petropoulos
Keyword(s):  
Soil Moisture ◽  
Land Surface ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Heat Fluxes ◽  
Surface Model ◽  
Landsat 8 ◽  
Simple Method ◽  
Practical Applications ◽  
Infrared Measurements

Earth Observation (EO) provides a promising approach towards deriving accurate spatiotemporal estimates of key parameters characterizing land surface interactions, such as latent (LE) and sensible (H) heat fluxes as well as soil moisture content. This paper proposes a very simple method to implement, yet reliable to calculate evapotranspiration fraction (EF) and surface moisture availability (Mo) from remotely sensed imagery of Normalized Difference Vegetation Index (NDVI) and surface radiometric temperature (Tir). The method is unique in that it derives all of its information solely from these two images. As such, it does not depend on knowing ancillary surface or atmospheric parameters, nor does it require the use of a land surface model. The procedure for computing spatiotemporal estimates of these important land surface parameters is outlined herein stepwise for practical application by the user. Moreover, as the newly developedscheme is not tied to any particular sensor, it can also beimplemented with technologically advanced EO sensors launched recently or planned to be launched such as Landsat 8 and Sentinel 3. The latter offers a number of key advantages in terms of future implementation of the method and wider use for research and practical applications alike.

Environmental benefits of traditional irrigation ditches in the Sierra Nevada (Spain) ecosystem by analysing the spatial-temporal evolution of NDVI on different time scales

2021 ◽  
Author(s):  
Javier Aparicio ◽  
Rafael Pimentel ◽  
María José Polo
Keyword(s):  
Soil Moisture ◽  
Sierra Nevada ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Global Analysis ◽  
Environmental Benefits ◽  
Mountain Range ◽  
Mountain Area ◽  
Traditional Irrigation ◽  
Landsat Satellite

<p>In Mediterranean mountain regions, traditional irrigation systems still persist in areas where the  modernization approaches do not succeed in being operational. It is common that these systems alter the soil uses, vegetation distribution and hydrological natural regime. </p><p>This is the case of the extensive network of irrigation ditches in the Sierra Nevada Mountain Range in southeastern Spain (an UNESCO  Reserve of the Biosphere, with areas as Natural and National Park), which originated in Muslim times, and is still operational in some areas. These ditches have contributed to maintaining local agricultural systems and populations in basins dominated by snow conditions, and they constitute a traditional regulation of water resources in the area. The network is made up of two types of irrigation ditches: “careo” and irrigation ditches. The first, the "careo", collects the meltwater and infiltrates it along its course, maintaining a high level of soil moisture and favouring deep percolation volumes that can be later consumed by the population through springs and natural fountains. The second, the irrigation ones, are used to transport water from the natural sources to the agricultural plots downstream the mountain area. In 2014, several irrigation ditches were restored in the Natural Park. This is a chance to further explore and quantify the role of this network in the hydrological budget on a local basis.  </p><p>The aim of this work is to evaluate to what extent the existence of these intermittent water networks affects the evolution of the surrounding vegetation. For this, one of the restored systems,  the Barjas Ditch in the village of Cañar, with a successful water circulation along its way, was selected from the increase of the soil water content in the ditch influence area and, indirectly a differential development of vegetation. Two analyses are performed using remote sensing information. The Normalized Difference Vegetation Index, NDVI, which is a spectral index used to estimate the quantity, quality and development of vegetation that can therefore be used indirectly as an indicator of the state of soil moisture, was used as the indicator of evolution. For this purpose, a historical set of LandSat satellite images  (TM, ETM+ and OLI) has been used. On the one hand, a global analysis on the whole mountainous range was carried out, comparing NDVI patterns in areas affected and non-affected by the ditches. On the other hand, the restored  Barjas ditch is used to assess vegetation changes before and after the restoration.</p>

scholarly journals Evaluation of the AMSR2 L2 soil moisture product of JAXA on the Mongolian Plateau over seven years (2012–2018)

2019 ◽  
Vol 1 (11) ◽  
Author(s):  
Ichirow Kaihotsu ◽  
Jun Asanuma ◽  
Kentaro Aida ◽  
Dambaravjaa Oyunbaatar
Keyword(s):  
Soil Moisture ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Surface Soil ◽  
Surface Soil Moisture ◽  
Mongolian Plateau ◽  
Moisture Measurement ◽  
Rainfall Condition ◽  
Soil Moisture Measurement

Abstract This study evaluated the Advanced Microwave Scanning Radiometer 2 (AMSR2) L2 soil moisture product (ver. 3) using in situ hydrological observational data, acquired over 7 years (2012–2018), from a 50 × 50 km flat area of the Mongolian Plateau covered with bare soil, pasture and shrubs. Although AMSR2 slightly underestimated soil moisture content at 3-cm depth, satisfactory timing was observed in both the response patterns and the in situ soil moisture data, and the differences between these factors were not large. In terms of the relationship between AMSR2 soil moisture from descending orbits and in situ measured soil moisture at 3-cm depth, the values of the RMSE (m3/m3) and the bias (m3/m3) varied from 0.028 to 0.063 and from 0.011 to − 0.001 m3/m3, respectively. The values of the RMSE and bias depended on rainfall condition. The mean value of the RMSE for the 7-year period was 0.042 m3/m3, i.e., lower than the target accuracy 0.050 m3/m3. The validation results for descending orbits were found slightly better than for ascending orbits. Comparison of the Soil Moisture and Ocean Salinity (SMOS) soil moisture product with the AMSR2 L2 soil moisture product showed that AMSR2 could observe surface soil moisture with nearly same accuracy and stability. However, the bias of the AMSR2 soil moisture measurement was slightly negative and poorer than that of SMOS with deeper soil moisture measurement. It means that AMSR2 cannot effectively measure soil moisture at 3-cm depth. In situ soil temperature at 3-cm depth and surface vegetation (normalized difference vegetation index) did not influence the underestimation of AMSR2 soil moisture measurements. These results suggest that a possible cause of the underestimation of AMSR2 soil moisture measurements is the difference between the depth of the AMSR2 observations and in situ soil moisture measurements. Overall, this study proved the AMSR2 L2 soil moisture product has been useful for monitoring daily surface soil moisture over large grassland areas and it clearly demonstrated the high-performance capability of AMSR2 since 2012.

scholarly journals Soil Moisture and Irrigation Mapping in A Semi-Arid Region, Based on the Synergetic Use of Sentinel-1 and Sentinel-2 Data

2018 ◽  
Vol 10 (12) ◽  
pp. 1953 ◽  
Author(s):  
Safa Bousbih ◽  
Mehrez Zribi ◽  
Mohammad El Hajj ◽  
Nicolas Baghdadi ◽  
Zohra Lili-Chabaane ◽  
...  
Keyword(s):  
Soil Moisture ◽  
Arid Region ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Cloud Model ◽  
Remotely Sensed Data ◽  
Semi Arid Region ◽  
Semi Arid ◽  
Sentinel 2 ◽  
Reference Fields

This paper presents a technique for the mapping of soil moisture and irrigation, at the scale of agricultural fields, based on the synergistic interpretation of multi-temporal optical and Synthetic Aperture Radar (SAR) data (Sentinel-2 and Sentinel-1). The Kairouan plain, a semi-arid region in central Tunisia (North Africa), was selected as a test area for this study. Firstly, an algorithm for the direct inversion of the Water Cloud Model (WCM) was developed for the spatialization of the soil water content between 2015 and 2017. The soil moisture retrieved from these observations was first validated using ground measurements, recorded over 20 reference fields of cereal crops. A second method, based on the use of neural networks, was also used to confirm the initial validation. The results reported here show that the soil moisture products retrieved from remotely sensed data are accurate, with a Root Mean Square Error (RMSE) of less than 5% between the two moisture products. In addition, the analysis of soil moisture and Normalized Difference Vegetation Index (NDVI) products over cultivated fields, as a function of time, led to the classification of irrigated and rainfed areas on the Kairouan plain, and to the production of irrigation maps at the scale of individual fields. This classification is based on a decision tree approach, using a combination of various statistical indices of soil moisture and NDVI time series. The resulting irrigation maps were validated using reference fields within the study site. The best results were obtained with classifications based on soil moisture indices only, with an accuracy of 77%.

scholarly journals Estimating Sahelian and East African soil moisture using the Normalized Difference Vegetation Index

2013 ◽  
Vol 10 (6) ◽  
pp. 7963-7997 ◽  
Author(s):  
A. McNally ◽  
C. Funk ◽  
G. J. Husak ◽  
J. Michaelsen ◽  
B. Cappelaere ◽  
...  
Keyword(s):  
Soil Moisture ◽  
Early Warning ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Agricultural Drought ◽  
Sub Saharan Africa ◽  
Sub Saharan ◽  
The Relationship ◽  
African Sahel

Abstract. Rainfall gauge networks in Sub-Saharan Africa are inadequate for assessing Sahelian agricultural drought, hence satellite-based estimates of precipitation and vegetation indices such as the Normalized Difference Vegetation Index (NDVI) provide the main source of information for early warning systems. While it is common practice to translate precipitation into estimates of soil moisture, it is difficult to quantitatively compare precipitation and soil moisture estimates with variations in NDVI. In the context of agricultural drought early warning, this study quantitatively compares rainfall, soil moisture and NDVI using a simple statistical model to translate NDVI values into estimates of soil moisture. The model was calibrated using in-situ soil moisture observations from southwest Niger, and then used to estimate root zone soil moisture across the African Sahel from 2001–2012. We then used these NDVI-soil moisture estimates (NSM) to quantify agricultural drought, and compared our results with a precipitation-based estimate of soil moisture (the Antecedent Precipitation Index, API), calibrated to the same in-situ soil moisture observations. We also used in-situ soil moisture observations in Mali and Kenya to assess performance in other water-limited locations in sub Saharan Africa. The separate estimates of soil moisture were highly correlated across the semi-arid, West and Central African Sahel, where annual rainfall exhibits a uni-modal regime. We also found that seasonal API and NDVI-soil moisture showed high rank correlation with a crop water balance model, capturing known agricultural drought years in Niger, indicating that this new estimate of soil moisture can contribute to operational drought monitoring. In-situ soil moisture observations from Kenya highlighted how the rainfall-driven API needs to be recalibrated in locations with multiple rainy seasons (e.g., Ethiopia, Kenya, and Somalia). Our soil moisture estimates from NDVI, on the other hand, performed well in Niger, Mali and Kenya. This suggests that the NDVI-soil moisture relationship may be more robust across rainfall regimes than the API because the relationship between NDVI and plant available water is less reliant on local characteristics (e.g., infiltration, runoff, evaporation) than the relationship between rainfall and soil moisture.

Sign in / Sign up

Export Citation Format

Share Document