scholarly journals The Impact of Contributor Confidence, Expertise and Distance on the Crowdsourced Land Cover Data Quality

Author(s):  
2021 ◽  
Author(s):  
Sebastian Drost ◽  
Fabian Netzel ◽  
Andreas Wytzisk-Ahrens ◽  
Christoph Mudersbach

<p>The application of Deep Learning methods for modelling rainfall-runoff have reached great advances in the last years. Especially, long short-term memory (LSTM) networks have gained enhanced attention for time-series prediction. The architecture of this special kind of recurrent neural network is optimized for learning long-term dependencies from large time-series datasets. Thus, different studies proved the applicability of LSTM networks for rainfall-runoff predictions and showed, that they are capable of outperforming other types of neural networks (Hu et al., 2018).</p><p>Understanding the impact of land-cover changes on rainfall-runoff dynamics is an important task. Such a hydrological modelling problem typically is solved with process-based models by varying model-parameters related to land-cover-incidents at different points in time. Kratzert et al. (2019) proposed an adaption of the standard LSTM architecture, called Entity-Aware-LSTM (EA-LSTM), which can take static catchment attributes as input features to overcome the regional modelling problem and provides a promising approach for similar use cases. Hence, our contribution aims to analyse the suitability of EA-LSTM for assessing the effect of land-cover changes.</p><p>In different experimental setups, we train standard LSTM and EA-LSTM networks for multiple small subbasins, that are associated to the Wupper region in Germany. Gridded daily precipitation data from the REGNIE dataset (Rauthe et al., 2013), provided by the German Weather Service (DWD), is used as model input to predict the daily discharge for each subbasin. For training the EA-LSTM we use land cover information from the European CORINE Land Cover (CLC) inventory as static input features. The CLC inventory includes Europe-wide timeseries of land cover in 44 classes as well as land cover changes for different time periods (Büttner, 2014). The percentage proportion of each land cover class within a subbasin serves as static input features. To evaluate the impact of land cover data on rainfall-runoff prediction, we compare the results of the EA-LSTM with those of the standard LSTM considering different statistical measures as well as the Nash–Sutcliffe efficiency (NSE).</p><p>In addition, we test the ability of the EA-LSTM to outperform physical process-based models. For this purpose, we utilize existing and calibrated hydrological models within the Wupper basin to simulate discharge for each subbasin. Finally, performance metrics of the calibrated model are used as benchmarks for assessing the performance of the EA-LSTM model.</p><p><strong>References</strong></p><p>Büttner, G. (2014). CORINE Land Cover and Land Cover Change Products. In: Manakos & M. Braun (Hrsg.), Land Use and Land Cover Mapping in Europe (Bd. 18, S. 55–74). Springer Netherlands. https://doi.org/10.1007/978-94-007-7969-3_5</p><p>Hu, C., Wu, Q., Li, H., Jian, S., Li, N., & Lou, Z. (2018). Deep Learning with a Long Short-Term Memory Networks Approach for Rainfall-Runoff Simulation. Water, 10(11), 1543. https://doi.org/10.3390/w10111543</p><p>Kratzert, F., Klotz, D., Shalev, G., Klambauer, G., Hochreiter, S., & Nearing, G. (2019). Towards learning universal, regional, and local hydrological behaviors via machine learning applied to large-sample datasets. Hydrology and Earth System Sciences, 23(12), 5089–5110. https://doi.org/10.5194/hess-23-5089-2019</p><p>Rauthe, M, Steiner, H, Riediger, U, Mazurkiewicz, A &Gratzki, A (2013): A Central European precipitation climatology – Part I: Generation and validation of a high-resolution gridded daily data set (HYRAS), Meteorologische Zeitschrift, Vol 22, No 3, 235–256. https://doi.org/10.1127/0941-2948/2013/0436</p>


2009 ◽  
Vol 30 (13) ◽  
pp. 1942-1953 ◽  
Author(s):  
Elif Sertel ◽  
Alan Robock ◽  
Cankut Ormeci

2012 ◽  
Vol 6 (1) ◽  
pp. 33-41 ◽  
Author(s):  
K. V.S. Badarinath ◽  
D. V. Mahalakshmi ◽  
Satyaban Bishoyi Ratna

Land-surface processes are one of the important drivers for weather and climate systems over the tropics. Realistic representation of land surface processes in mesoscale models over the region will help accurate simulation of numerical forecasts. The present study examines the influence of Land Use/ Land Cover Change (LULC) on the forecasting of cyclone intensity and track prediction using Mesoscale Model (MM5). Gridded land use/land cover data set over the Indian region compatible with the MM5 model were generated from Indian Remote Sensing Satellite (IRS-P6) Advanced Wide Field Sensor (AWiFS) for the year 2007-2008. A case study of simulation of ‘Aila’ cyclone has been considered to see the impact of these two sets of LULC data with the use of MM5 model. Results of the study indicated that incorporation of current land use/land cover data sets in mesoscale model provides better forecasting of cyclonic track.


Atmosphere ◽  
2020 ◽  
Vol 11 (11) ◽  
pp. 1242
Author(s):  
Erika Danaé López-Espinoza ◽  
Jorge Zavala-Hidalgo ◽  
Rezaul Mahmood ◽  
Octavio Gómez-Ramos

In atmospheric modeling, an accurate representation of land cover is required because such information impacts water and energy budgets and, consequently, the performance of models in simulating regional climate. This study analyzes the impact of the land cover data on an operational weather forecasting system using the Weather Research and Forecasting (WRF) model for central Mexico, with the aim of improving the quality of the operative forecast. Two experiments were conducted using different land cover datasets: a United States Geological Survey (USGS) map and an updated North American Land Change Monitoring System (NALCMS) map. The experiments were conducted as a daily 120 h forecast for each day of January, April, July, and September of 2012, and the near-surface temperature, wind speed, and hourly precipitation were analyzed. Both experiments were compared with observations from meteorological stations. The statistical analysis of this study showed that wind speed and near-surface temperature prediction may be further improved with the updated and more accurate NALCMS dataset, particularly in the forecast covering 48 to 72 h. The Root Mean Square Error (RMSE) of the average wind speed reached a maximum reduction of up to 1.2 m s−1, whereas for the near-surface temperature there was a reduction of up to 0.6 °C. The RMSE of the average hourly precipitation was very similar between both experiments, however the location of precipitation was modified.


Circulation ◽  
2014 ◽  
Vol 130 (suppl_2) ◽  
Author(s):  
Mohan Thanikachalam ◽  
Kevin J Lane ◽  
Jahnavi Sunderarajan ◽  
Vijaykumar Harivanzan ◽  
Sadagopan Thanikachalam

Background: Urbanization is linked to higher prevalence of cardiovascular disease (CVD). Hypertension (HTN) is a major risk factor for CVD. In this study we assess the impact of urbanization on prevalence of HTN in a population-based study in South India. Methods: In the cross-sectional analysis 8080 participants (mean age 42 years; 58% women) spread over 65 x 80 km area constituted the study sample. MODIS satellite derived land cover data at a 1 km x 1 km resolution was obtained and joined to each participant’s geolocated residential position in ArcGIS to assign urban and rural (crops, trees, shrubs and grass land cover) designations. Simultaneously, participants’ residential position in relation to urban center was assessed. The study included sytolic (SBP) and diastolic (DBP) blood pressure, anthropometric, socioeconomic, psycosocial, physcial activity assessemnts and blood work. HTN was defined as SBP ≥ 140 or DBP ≥ 90 or reported history of HTN. Results: Based on the land cover data the mean SBP and DBP (mmHg) in men (SBP: 131 ± 21; DBP: 81 ± 12) and women (SBP: 125 ± 20; DBP: 77 ± 11) living in urban environment were significantly higher when compared to men (SBP: 122 ± 18; DBP: 77 ± 11) and women (SBP: 117 ± 18; DBP: 74 ± 10) in rural environments [p < 0.001]. There was a significantly higher prevalence of HTN in urban men (42.1%) when compared to rural men (26.4%) [p < 0.001]. Similarly, the prevalence of HTN was higher in urban women (28.3%), when compared to rural women (19.1%) [p < 0.001]. After controlling for age, BMI, smoking, blood sugar, LDL and socioeconomic, physical activity, anxiety and stress levels, both men (OR = 1.94; 95% CI: 1.64, 2.9) and women (OR = 1.51; 95% CI: 1.28, 1.8) living in urban land cover were more likely to have HTN compared to those living in non-urban land cover. In the proximity analysis after multivariate adjustments, men (OR = 2.25; 95%CI: 1.78, 2.83) and women (OR = 1.87; 95%CI: 1.47, 2.38) residing within 0-20 km distance from urban center had significantly higher odds of HTN than the 60-80 km reference group. Conclusions: Living in an urban environment is associated with increased prevalence of HTN independent of other risk factors. Future research is needed to determine what components of the urban environment contribute to increased levels of HTN.


2016 ◽  
Vol 18 (6) ◽  
pp. 961-974 ◽  
Author(s):  
Younggu Her ◽  
Conrad Heatwole

Parameter uncertainty in hydrologic modeling is commonly evaluated, but assessing the impact of spatial input data uncertainty in spatially descriptive ‘distributed’ models is not common. This study compares the significance of uncertainty in spatial input data and model parameters on the output uncertainty of a distributed hydrology and sediment transport model, HYdrology Simulation using Time-ARea method (HYSTAR). The Shuffled Complex Evolution Metropolis (SCEM-UA) algorithm was used to quantify parameter uncertainty of the model. Errors in elevation and land cover layers were simulated using the Sequential Gaussian/Indicator Simulation (SGS/SIS) techniques and then incorporated into the model to evaluate their impact on the outputs relative to those of the parameter uncertainty. This study demonstrated that parameter uncertainty had a greater impact on model output than did errors in the spatial input data. In addition, errors in elevation data had a greater impact on model output than did errors in land cover data. Thus, for the HYSTAR distributed hydrologic model, accuracy and reliability can be improved more effectively by refining parameters rather than further improving the accuracy of spatial input data and by emphasizing the topographic data over the land cover data.


2014 ◽  
Vol 34 (suppl_1) ◽  
Author(s):  
Mohan Thanikachalam ◽  
Kevin Lane ◽  
Jahnavi Sunderarajan ◽  
Laura Corlin ◽  
Vijaykumar Harivanzan ◽  
...  

Background: Rapid urbanization is driving economies of South Asian countries. Here we use satellite based land cover data and distance to urban center (UC) to measure of the impact of urban environment on arterial stiffness (AS) in a population based study in South India. Methods: In a cross-sectional analysis, after exclusion of people with previous history of diabetes and hypertension, 6746 subjects (mean age 42 years; 54% women) spread over 78 kms from the UC constituted the study sample. MODIS satellite derived land cover data at a 1 km x 1 km resolution was obtained and joined to each participant's geolocated residential position in ArcGIS to assign urban and rural designations. The study included carotid-femoral pulse wave velocity (PWV) measurement using a high-fidelity applanation tonometry, blood pressure (BP), anthropometric, psychosocial, high sensitive C-reactive protein (HsCRP) and other biomarkers assessments. Results: Based on land cover analysis, participants in urban locations had a mean (SD) PWV (m/s) of 7.74 (1.65) compared to 7.6 (1.62) in rural locations (p= 0.002) [Fig 1], while there was no significant difference in HsCRP levels. In multiple regression analyses adjusting for age, smoking, BMI, BP, blood glucose, LDL, socioeconomic, anxiety and stress levels, distance from UC was independently associated with PWV in men (β = -0.007, p <0.001), but not in women. Standardized effect-estimates in the multi-linear regression model indicated that distance from UC had the third largest effect on PWV after age and BP. After multivariable adjustments, the largest effect of distance from UC on PWV was on non-smoking men age 46-75 years. Residing every 1 km further away from the UC corresponded with a -0.012 m/s (95%CI: -0.020, -0.003) decrease in PWV. Conclusions: Urbanization is an independent predictor of AS in men, more so in non-smoking older men. Further research will elucidate components in the urban environment that may be contributing to higher AS.


Sign in / Sign up

Export Citation Format

Share Document