scholarly journals Prediction of Severe Drought Area Based on Random Forest: Using Satellite Image and Topography Data

Water ◽  
2019 ◽  
Vol 11 (4) ◽  
pp. 705 ◽  
Author(s):  
Haekyung Park ◽  
Kyungmin Kim ◽  
Dong kun Lee
Keyword(s):  
Soil Moisture ◽  
Random Forest ◽  
Meteorological Data ◽  
Satellite Image ◽  
Remote Sensing Data ◽  
Absolute Error ◽  
Severe Drought ◽  
Drought Forecasting ◽  
Moisture Index ◽  
Training Area

The uncertainty of drought forecasting based on past meteorological data is increasing because of climate change. However, agricultural droughts, associated with food resources and determined by soil moisture, must be predicted several months ahead for timely resource allocation. Accordingly, we designed a severe drought area prediction (SDAP) model for short-term drought without meteorological data. The predictions of our proposed SDAP model indicate a forecast of serious drought areas assuming non-rainfall, not a probability prediction of drought occurrence. Furthermore, this prediction provides more practical information to help with rapid water allocation during a real drought. The model structure using remote sensing data consists of two parts. First, the drought function f(x) from the training area by random forest (RF) learned the changes in the pattern of soil moisture index (SMI) from the past drought and the training performance was found to be root mean square error (RMSE) = 0.052, mean absolute error (MAE) = 0.039, R2 = 0.91. Second, derived f(x) predicted the SMI of the study area, which is 20 times larger than the training area, of the same season of another year as RMSE = 0.382, MAE = 0.375, R2 = 0.58. We also obtained the variable importance stemming from RF and discussed its meaning along with the advantages and limitations of the model, training areas selection, and prediction coverage.

scholarly journals Estimating 500-m Resolution Soil Moisture Using Sentinel-1 and Optical Data Synergy

Water ◽  
2020 ◽  
Vol 12 (3) ◽  
pp. 866 ◽  
Author(s):  
Myriam Foucras ◽  
Mehrez Zribi ◽  
Clément Albergel ◽  
Nicolas Baghdadi ◽  
Jean-Christophe Calvet ◽  
...  
Keyword(s):  
Soil Moisture ◽  
Optical Sensors ◽  
Surface Soil ◽  
Remote Sensing Data ◽  
Climatic Conditions ◽  
Optical Data ◽  
Surface Soil Moisture ◽  
Moisture Index ◽  
Wide Range ◽  
Moderate Resolution Imaging Spectroradiometer

The aim of this study is to estimate surface soil moisture at a spatial resolution of 500 m and a temporal resolution of at least 6 days, by combining remote sensing data from Sentinel-1 and optical data from Sentinel-2 and MODIS (Moderate-Resolution Imaging Spectroradiometer). The proposed methodology is based on the change detection technique, applied to a series of measurements over a three-year period (2015 to 2018). The algorithm described here as “Soil Moisture Estimations from the Synergy of Sentinel-1 and optical sensors (SMES)” proposes different options, allowing information from vegetation densities and seasonal conditions to be taken into account. The output from this algorithm is a moisture index ranging between 0 and 1, with 0 corresponding to the driest soils and 1 to the wettest soils. This methodology has been tested at different test sites (South of France, Central Tunisia, Western Benin and Southwestern Niger), characterized by a wide range of different climatic conditions. The resulting surface soil moisture estimations are compared with in situ measurements and already existing satellite-derived soil moisture ASCAT (Advanced SCATterometer) products. They are found to be well correlated, for the African regions in particular (RMSE below 6 vol.%). This outcome indicates that the proposed algorithm can be used with confidence to estimate the surface soil moisture of a wide range of climatically different sites.

scholarly journals Monitoring and Assessment of Salinity and Chemicals in Agricultural Lands by a Remote Sensing Technique and Soil Moisture with Chemical Index Models

Geosciences ◽  
2020 ◽  
Vol 10 (6) ◽  
pp. 207 ◽  
Author(s):  
Hashim Ali Hasab ◽  
Hayder Dibs ◽  
Abdulameer Sulaiman Dawood ◽  
Wurood Hasan Hadi ◽  
Hussain M. Hussain ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Soil Moisture ◽  
Soil Quality ◽  
Agricultural Land ◽  
Remote Sensing Data ◽  
Quality Parameters ◽  
Chemical Pollution ◽  
Landsat 8 ◽  
Moisture Index ◽  
Chemical Index

Agricultural land in the south of Iraq provides habitat for several types of living creatures. This land has a significant impact on the ecosystem. The agricultural land of Al-Hawizeh marsh covers an area of more than 3500 km2 and is considered an enriched resource to produce several harvests. A total of 74% of this area suffers from a high degree of salinity and chemical pollution, which needs to be remedied. Several human-made activities and post-war-related events have caused radical deterioration in soil quality in the agricultural land. The goal of this research was to integrate mathematical models, remote sensing data, and GIS to provide a powerful tool to predict, assess, monitor, manage, and map the salinity and chemical parameters of iron (Fe), lead (Pb), copper (Cu), chromium (Cr), and zinc (Zn) in the soils of agricultural land in Al-Hawizeh marsh in southern Iraq during the four seasons of 2017. The mathematical model consists of four parts. The first depends on the B6 and B11 bands of Landsat-8, to calculate the soil moisture index (SMI). The second is the salinity equation (SE), which depends on the SMI result to retrieve the salinity values from Landsat-8 images. The third part depends on the B6 and B7 bands of Landsat-8, which calculates the clay chemical index (CCIs). The fourth part is the chemical equation (CE), which depends on the CCI to retrieve the chemical values (Fe, Pb, Cu, Cr, and Zn) from Landsat-8 images. The average salinity concentrations during autumn, summer, spring, and winter were 1175, 1010, 1105, and 1789 mg/dm3, respectively. The average Fe concentrations during autumn, summer, spring and winter were 813, 784, 842, and 1106 mg/dm3, respectively. The average Pb concentrations during autumn, summer, spring, and winter were 4.85, 3.79, 4.74, and 7.2 mg/dm3, respectively. The average Cu concentrations during autumn, summer, spring, and winter were 3.9, 3.1, 4.45, and 7.5 mg/dm3, respectively. The average Cr concentrations during autumn, summer, spring, and winter seasons were 1.28, 0.73, 1.03, and 2.91 mg/dm3, respectively. Finally, the average Zn concentrations during autumn, summer, spring, and winter were 8.25, 6, 7.05, and 12 mg/dm3, respectively. The results show that the concentrations of salinity and chemicals decreased in the summer and increased in the winter. The decision tree (DT) classification depended on the output results for salinity and chemicals for both SE and CE equations. This classification refers to all the parameters simultaneously in one stage. The output of DT classification results can display all the soil quality parameters (salinity, Fe, Pb, Cu, Cr, and Zn) in one image. This approach was repeated for each season in this study. In conclusion, the developed systematic and generic approach may constitute a basis for determining soil quality parameters in agricultural land worldwide.

Seasonal forecast of agricultural impacts of droughts in Mexico through a principal component regression based approach

2020 ◽  
Author(s):  
Roberto Real-Rangel ◽  
Adrián Pedrozo-Acuña ◽  
Agustín Breña-Naranjo
Keyword(s):  
Soil Moisture ◽  
Regional Scale ◽  
Principal Component Regression ◽  
Principal Component ◽  
Drought Monitoring ◽  
Drought Forecasting ◽  
Moisture Index ◽  
The North ◽  
Wide Range ◽  
Monitoring And Forecasting

<p>Drought monitoring and forecasting allows to adopt mitigating actions in early stages of an event to reduce the vulnerability of a wide range of environmetal, economical and social sectors. In Mexico, various drought monitoring systems on national and regional scale perform a follow up of these events, such as the Drought Monitor in Mexico, and the North American Drought Monitor, but seasonal drought forecasting is still a pending task. This study aims at fill this gap applying a methodology that uses data derived from a globally available atmospheric reanalysis product and a principal component regression based model oriented to predict drought impacts in rainfed crops associated to deficits in the soil moisture, estimated by means of the standardized soil moisture index (SSI). Using the state of Guanajuato (Center-North of Mexico) as a study case, the model generated yielded RSME values of 0.74 using regional and global hydrological, climatic and atmospheric variables as predictors with a lead-time of 4 months.</p>

scholarly journals PM2.5 Prediction Based on Random Forest, XGBoost, and Deep Learning Using Multisource Remote Sensing Data

Atmosphere ◽  
2019 ◽  
Vol 10 (7) ◽  
pp. 373 ◽  
Author(s):  
Mehdi Zamani Joharestani ◽  
Chunxiang Cao ◽  
Xiliang Ni ◽  
Barjeece Bashir ◽  
Somayeh Talebiesfandarani
Keyword(s):  
Deep Learning ◽  
Random Forest ◽  
Meteorological Data ◽  
Fine Particulate Matter ◽  
Model Performance ◽  
Remote Sensing Data ◽  
Health Concern ◽  
Gradient Boosting ◽  
High Concentration ◽  
Extreme Gradient Boosting

In recent years, air pollution has become an important public health concern. The high concentration of fine particulate matter with diameter less than 2.5 µm (PM2.5) is known to be associated with lung cancer, cardiovascular disease, respiratory disease, and metabolic disease. Predicting PM2.5 concentrations can help governments warn people at high risk, thus mitigating the complications. Although attempts have been made to predict PM2.5 concentrations, the factors influencing PM2.5 prediction have not been investigated. In this work, we study feature importance for PM2.5 prediction in Tehran’s urban area, implementing random forest, extreme gradient boosting, and deep learning machine learning (ML) approaches. We use 23 features, including satellite and meteorological data, ground-measured PM2.5, and geographical data, in the modeling. The best model performance obtained was R2 = 0.81 (R = 0.9), MAE = 9.93 µg/m3, and RMSE = 13.58 µg/m3 using the XGBoost approach, incorporating elimination of unimportant features. However, all three ML methods performed similarly and R2 varied from 0.63 to 0.67, when Aerosol Optical Depth (AOD) at 3 km resolution was included, and 0.77 to 0.81, when AOD at 3 km resolution was excluded. Contrary to the PM2.5 lag data, satellite-derived AODs did not improve model performance.

scholarly journals Agricultural Drought Monitoring by MODIS Potential Evapotranspiration Remote Sensing Data Application

2020 ◽  
Vol 12 (20) ◽  
pp. 3411
Author(s):  
Kamil Szewczak ◽  
Helena Łoś ◽  
Rafał Pudełko ◽  
Andrzej Doroszewski ◽  
Łukasz Gluba ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Potential Evapotranspiration ◽  
Meteorological Data ◽  
Measurement Data ◽  
Remote Sensing Data ◽  
Absolute Error ◽  
Agricultural Drought ◽  
Drought Monitoring ◽  
Trend Test ◽  
Sensing Data

The current Polish Agricultural Drought Monitoring System (ADMS) adopted Climatic Water Balance (CWB) as the main indicator of crop losses caused by drought conditions. All meteorological data needed for CWB assessment are provided by the ground meteorological stations network. In 2018, the network consisted of 665 stations, among which in only 58 stations full weather parameters were registered. Therefore, only these stations offered a possibility to estimate the exact values of potential evapotranspiration, which is a component of the CWB algorithm. This limitation affects the quality of CWB raster maps, interpolated on the basis of the meteorological stations network for the entire country. However, the interpolation process itself may introduce errors; therefore, the adaptation of satellite data (that are spatially continuous) should be taken into account, even if the lack of data due to cloudiness remains a serious problem. In this paper, we involved the remote sensing data from MODIS instrument and considered the ability to integrate those data with values determined by using ground measurements. The paper presents results of comparisons for the CWB index assessed using ground station data and those obtained from potential evapotranspiration as the product from Moderate Resolution Imaging Spectroradiometer (MODIS) remote sensing instrument. The comparisons of results were performed for specific points (locations of ground stations) and were expressed by differences in means values. Analysis of Pearson’s correlation coefficient (r), Mann–Kendal trend test (Z-index), mean absolute error (MAE) and root mean square error (RMSE) for ten years’ series were evaluated and are presented. In addition, the basic spatial interpretation of results has been proposed. The correlation test revealed the r coefficient in the range from 0.06 to 0.68. The results show good trend agreement in time between two types of CWB with constantly higher values of this index, which is estimated using ground measurement data. In results for 34 (from 43 analyzed) stations the Mann–Kendal test provide the consistent trend, and only nine trends were inconsistent. Analyses revealed that the disagreement between the two considered indices (determined in different ways) increased significantly in the warmer period with a significant break point between R7 and R8 that falls at the end of May for each examined year. The value of MAE varied from 80 mm to 135 mm.

scholarly journals AGRICULTURAL DROUGHT AND SOIL MOISTURE ANALYSIS USING SATELLITE IMAGE BASED INDICES

2019 ◽  
Vol XLII-3/W6 ◽  
pp. 507-514
Author(s):  
S. Sreekesh ◽  
N. Kaur ◽  
S. R. Sreerama Naik
Keyword(s):  
Soil Moisture ◽  
Satellite Image ◽  
Condition Index ◽  
Agricultural Drought ◽  
Drought Severity ◽  
Severe Drought ◽  
Landsat Images ◽  
Moisture Conditions ◽  
The Impact ◽  
Meteorological Droughts

<p><strong>Abstract.</strong> The deficiency in rainfall leads to meteorological droughts. Its manifestations are visible both in the vegetation cover and soil moisture. The present study assessed the characteristics of agricultural drought following meteorological droughts. The study also assessed the severity of meteorological droughts and their manifestation on the agriculture and soil moisture in a semi-arid area. The study has been carried out for the Malaprabha sub-basin which partly covers three districts of North Interior Karnataka, India. India Meteorological Department’s (IMD) criteria have been used to identify the drought years, and its severity has been assessed through the Standard Precipitation Index (SPI). The IMD’s monthly rainfall data were used to identify the drought years and periods for the region. Among the drought years, the mild, moderate, and severe drought along with deficit and excess rainfall years were considered to assess and characterize the soil moisture conditions and the agricultural drought. The satellite image based indices for these selected years were constructed to determine the soil moisture conditions and the agricultural drought severity. The Temperature-Vegetation Dryness Index (TVDI) was used to determine the soil moisture conditions. The indices employed to determine the agriculture drought are NDVI, Thermal Condition Index (TCI), Vegetation Condition Index (VCI), and Vegetation Health Index (VHI). These satellite-based indices were calculated using the Landsat images of the selected drought and non-drought years. The results showed that the seasonal and annual drought are frequent in the study area. There are spatial and temporal variations in the drought years and their severity. The satellite-based indices clearly indicate the spatial variation in the agriculture droughts and its intensity. It has been found that the impact of drought on agriculture has significantly reduced due to the development of well-irrigation in the sub-basin. VHI is more appropriate in determining the agricultural drought and its characteristics.</p>

scholarly journals Spatial Evaluation of Soil Moisture (SM), Land Surface Temperature (LST), and LST-Derived SM Indexes Dynamics during SMAPVEX12

Sensors ◽  
2019 ◽  
Vol 19 (5) ◽  
pp. 1247 ◽  
Author(s):  
Hao Sun ◽  
Baichi Zhou ◽  
Hongxing Liu
Keyword(s):  
Soil Moisture ◽  
Surface Temperature ◽  
Land Surface Temperature ◽  
Land Surface ◽  
Meteorological Data ◽  
Remote Sensing Data ◽  
Surface Radiation ◽  
Spatial Correlations ◽  
Application Potential ◽  
Decoupling Effect

Downscaling microwave soil moisture (SM) with optical/thermal remote sensing data has considerable application potential. Spatial correlations between SM and land surface temperature (LST) or LST-derived SM indexes (SMIs) are vital to the current optical/thermal and microwave fusion downscaling methods. In this study, the spatial correlations were evaluated at the same spatial scale using SMAPVEX12 SM data and MODIS day/night LST products. LST-derived SMIs was calculated using NLDAS-2 gridded meteorological data with conventional trapezoid and two-stage trapezoid models. Results indicated that (1) SM agrees better with daytime LST than the nighttime or the day-night differential LST; (2) the daytime LSTs on Aqua and Terra present very similar spatial agreement with SM and they have very similar performances as downscaling factors in simulating SM; (3) decoupling effect among SM, LST, and LST-derived SMIs occurs not only in very wet but also in very dry condition; and (4) the decoupling effect degrades the performance of LST as a downscaling factor. The future downscaling algorithms should consider net surface radiation and soil type to tackle the decoupling effect.

scholarly journals Decomposition-Based Soil Moisture Estimation Using UAVSAR Fully Polarimetric Images

Agronomy ◽  
2021 ◽  
Vol 11 (1) ◽  
pp. 145
Author(s):  
Zeinab Akhavan ◽  
Mahdi Hasanlou ◽  
Mehdi Hosseini ◽  
Heather McNairn
Keyword(s):  
Machine Learning ◽  
Feature Selection ◽  
Soil Moisture ◽  
Random Forest ◽  
Performance Enhancement ◽  
Learning Algorithms ◽  
Absolute Error ◽  
Machine Learning Algorithms ◽  
Eigenvalue And Eigenvector ◽  
Moisture Estimation

Polarimetric decomposition extracts scattering features that are indicative of the physical characteristics of the target. In this study, three polarimetric decomposition methods were tested for soil moisture estimation over agricultural fields using machine learning algorithms. Features extracted from model-based Freeman–Durden, Eigenvalue and Eigenvector based H/A/α, and Van Zyl decompositions were used as inputs in random forest and neural network regression algorithms. These algorithms were applied to retrieve soil moisture over soybean, wheat, and corn fields. A time series of polarimetric Uninhabited Aerial Vehicle Synthetic Aperture Radar (UAVSAR) data acquired during the Soil Moisture Active Passive Experiment 2012 (SMAPVEX12) field campaign was used for the training and validation of the algorithms. Three feature selection methods were tested to determine the best input features for the machine learning algorithms. The most accurate soil moisture estimates were derived from the random forest regression algorithm for soybeans, with a correlation of determination (R2) of 0.86, root mean square error (RMSE) of 0.041 m3 m−3 and mean absolute error (MAE) of 0.030 m3 m−3. Feature selection also impacted results. Some features like anisotropy, Horizontal transmit and Horizontal receive (HH), and surface roughness parameters (correlation length and RMS-H) had a direct effect on all algorithm performance enhancement as these parameters have a direct impact on the backscattered signal.

scholarly journals A baseline probabilistic drought forecasting framework using standardized soil moisture index: application to the 2012 United States drought

2014 ◽  
Vol 18 (7) ◽  
pp. 2485-2492 ◽  
Author(s):  
A. AghaKouchak
Keyword(s):  
United States ◽  
Soil Moisture ◽  
Rapid Development ◽  
Critical Time ◽  
Commodity Prices ◽  
The United States ◽  
Drought Forecasting ◽  
Moisture Index ◽  
Drought Prediction ◽  
Persistence Property

Abstract. The 2012 drought was one of the most extensive drought events in half a century, resulting in over USD 12 billion in economic loss in the United States and substantial indirect impacts on global food security and commodity prices. An important feature of the 2012 drought was rapid development and intensification in late spring/early summer, a critical time for crop development and investment planning. Drought prediction remains a major challenge because dynamical precipitation forecasts are highly uncertain, and their prediction skill is low. Using a probabilistic framework for drought forecasting based on the persistence property of accumulated soil moisture, this paper shows that the US drought of summer 2012 was predictable several months in advance. The presented drought forecasting framework provides the probability occurrence of drought based on climatology and near-past observations of soil moisture. The results indicate that soil moisture exhibits higher persistence than precipitation, and hence improves drought predictability.

scholarly journals Soil Moisture Retrieval by Integrating TASI-600 Airborne Thermal Data, WorldView 2 Satellite Data and Field Measurements: Petacciato Case Study

Sensors ◽  
2019 ◽  
Vol 19 (7) ◽  
pp. 1515 ◽  
Author(s):  
Angelo Palombo ◽  
Simone Pascucci ◽  
Antonio Loperte ◽  
Antonio Lettino ◽  
Fabio Castaldi ◽  
...  
Keyword(s):  
Soil Moisture ◽  
Near Infrared ◽  
Water Cycle ◽  
Satellite Image ◽  
Thermal Inertia ◽  
Remote Sensing Data ◽  
Field Measurements ◽  
Calibration Procedure ◽  
Soil Samples ◽  
Terrestrial Water

Soil moisture (SM) plays a fundamental role in the terrestrial water cycle and in agriculture, with key applications such as the monitoring of crop growing and hydrogeological management. In this study, a calibration procedure was applied to estimate SM based on the integration of in situ and airborne thermal remote sensing data. To this aim, on April 2018, two airborne campaigns were carried out with the TASI-600 multispectral thermal sensor on the Petacciato (Molise, Italy) area. Simultaneously, soil samples were collected in different agricultural fields of the study area to determine their moisture content and the granulometric composition. A WorldView 2 high-resolution visible-near infrared (VNIR) multispectral satellite image was acquired to calculate the albedo of the study area to be used together with the TASI images for the estimation of the apparent thermal inertia (ATI). Results show a good correlation (R2 = 0.62) between the estimated ATI and the SM of the soil samples measured in the laboratory. The proposed methodology has allowed us to obtain a SM map for bare and scarcely vegetated soils in a wide agricultural area in Italy which concerns cyclical hydrogeological instability phenomena.

Sign in / Sign up

Export Citation Format

Share Document