scholarly journals Large scale atmospheric forcing and topographic modification of precipitation rates over High Asia – a neural network based approach

2014 ◽  
Vol 5 (2) ◽  
pp. 1275-1317 ◽  
Author(s):  
L. Gerlitz ◽  
O. Conrad ◽  
J. Böhner
Keyword(s):  
Neural Network ◽  
High Resolution ◽  
Spatial Resolution ◽  
Large Scale ◽  
Local Scale ◽  
Predictor Variables ◽  
High Mountain ◽  
Target Area ◽  
Monthly Precipitation ◽  
The Tibetan Plateau

Abstract. The heterogeneity of precipitation rates in high mountain regions is not sufficiently captured by state of the art climate reanalysis products due to their limited spatial resolution. Thus there exists a large gap between the available data sets and the demands of climate impact studies. The presented approach aims to generate spatially high resolution precipitation fields for a target area in Central Asia, covering the Tibetan Plateau, the adjacent mountain ranges and lowlands. Based on the assumption, that observed local scale precipitation amounts are triggered by varying large scale atmospheric situations and modified by local scale topographic characteristics, the statistical downscaling approach estimates local scale precipitation rates as a function of large scale atmospheric conditions, derived from the ERA-Interim reanalysis, and high resolution terrain parameters. Since the relationships of the predictor variables with local scale observations are rather unknown and highly non-linear, an Artificial Neural Network (ANN) was utilized for the development of adequate transfer functions. Different ANN-architectures were evaluated with regard to their predictive performance. The final downscaling model was used for the cellwise estimation of monthly precipitation sums, the number of rainy days and the maximum daily precipitation amount with a spatial resolution of 1 km2. The model was found to sufficiently capture the temporal and spatial variations of precipitation rates in the highly structured target area and allows a detailed analysis of the precipitation distribution. A concluding sensitivity analysis of the ANN model reveals the effect of the atmospheric and topographic predictor variables on the precipitation estimations in the climatically diverse subregions.

scholarly journals Large-scale atmospheric forcing and topographic modification of precipitation rates over High Asia – a neural-network-based approach

2015 ◽  
Vol 6 (1) ◽  
pp. 61-81 ◽  
Author(s):  
L. Gerlitz ◽  
O. Conrad ◽  
J. Böhner
Keyword(s):  
Neural Network ◽  
High Resolution ◽  
Spatial Resolution ◽  
Large Scale ◽  
Local Scale ◽  
Predictor Variables ◽  
High Mountain ◽  
Target Area ◽  
Monthly Precipitation ◽  
Highly Nonlinear

Abstract. The heterogeneity of precipitation rates in high-mountain regions is not sufficiently captured by state-of-the-art climate reanalysis products due to their limited spatial resolution. Thus there exists a large gap between the available data sets and the demands of climate impact studies. The presented approach aims to generate spatially high resolution precipitation fields for a target area in central Asia, covering the Tibetan Plateau and the adjacent mountain ranges and lowlands. Based on the assumption that observed local-scale precipitation amounts are triggered by varying large-scale atmospheric situations and modified by local-scale topographic characteristics, the statistical downscaling approach estimates local-scale precipitation rates as a function of large-scale atmospheric conditions, derived from the ERA-Interim reanalysis and high-resolution terrain parameters. Since the relationships of the predictor variables with local-scale observations are rather unknown and highly nonlinear, an artificial neural network (ANN) was utilized for the development of adequate transfer functions. Different ANN architectures were evaluated with regard to their predictive performance. The final downscaling model was used for the cellwise estimation of monthly precipitation sums, the number of rainy days and the maximum daily precipitation amount with a spatial resolution of 1 km2. The model was found to sufficiently capture the temporal and spatial variations in precipitation rates in the highly structured target area and allows for a detailed analysis of the precipitation distribution. A concluding sensitivity analysis of the ANN model reveals the effect of the atmospheric and topographic predictor variables on the precipitation estimations in the climatically diverse subregions.

scholarly journals Downscaling of MODIS NDVI by Using a Convolutional Neural Network-Based Model with Higher Resolution SAR Data

2021 ◽  
Vol 13 (4) ◽  
pp. 732
Author(s):  
Ryota Nomura ◽  
Kazuo Oki
Keyword(s):  
Neural Network ◽  
High Resolution ◽  
Spatial Resolution ◽  
Temporal Resolution ◽  
High Spatial Resolution ◽  
Target Area ◽  
Modis Ndvi ◽  
Acceptable Accuracy ◽  
Sar Data ◽  
Sentinel 2

The normalized difference vegetation index (NDVI) is a simple but powerful indicator, that can be used to observe green live vegetation efficiently. Since its introduction in the 1970s, NDVI has been used widely for land management, food security, and physical models. For these applications, acquiring NDVI in both high spatial resolution and high temporal resolution is preferable. However, there is generally a trade-off between temporal and spatial resolution when using satellite images. To relieve this problem, a convolutional neural network (CNN) based downscaling model was proposed in this research. This model is capable of estimating 10-m high resolution NDVI from MODIS (Moderate Resolution Imaging Spectroradiometer) 250-m resolution NDVI by using Sentinel-1 10-m resolution synthetic aperture radar (SAR) data. First, this downscaling model was trained to estimate Sentinel-2 10-m resolution NDVI from a combination of upscaled 250-m resolution Sentinel-2 NDVI and 10-m resolution Sentinel-1 SAR data, by using data acquired in 2019 in the target area. Then, the generality of this model was validated by applying it to test data acquired in 2020, with the result that the model predicted the NDVI with reasonable accuracy (MAE = 0.090, ρ = 0.734 on average). Next, 250-m NDVI from MODIS data was used as input to confirm this model under conditions replicating an actual application case. Although there were mismatch in the original MODIS and Sentinel-2 NDVI data, the model predicted NDVI with acceptable accuracy (MAE = 0.108, ρ = 0.650 on average). Finally, this model was applied to predict high spatial resolution NDVI using MODIS and Sentinel-1 data acquired in target area from 1 January 2020~31 December 2020. In this experiment, double cropping of cabbage, which was not observable at the original MODIS resolution, was observed by enhanced temporal resolution of high spatial resolution NDVI images (approximately ×2.5). The proposed method enables the production of 10-m resolution NDVI data with acceptable accuracy when cloudless MODIS NDVI and Sentinel-1 SAR data is available, and can enhance the temporal resolution of high resolution 10-m NDVI data.

scholarly journals Deriving VIIRS High-Spatial Resolution Water Property Data over Coastal and Inland Waters Using Deep Convolutional Neural Network

2021 ◽  
Vol 13 (10) ◽  
pp. 1944
Author(s):  
Xiaoming Liu ◽  
Menghua Wang
Keyword(s):  
Neural Network ◽  
High Resolution ◽  
Spatial Resolution ◽  
High Spatial Resolution ◽  
Ocean Color ◽  
Super Resolution ◽  
Inland Waters ◽  
Coastal Oceans ◽  
Chl A ◽  
Color Data

The Visible Infrared Imaging Radiometer Suite (VIIRS) onboard the Suomi National Polar-orbiting Partnership (SNPP) satellite has been a reliable source of ocean color data products, including five moderate (M) bands and one imagery (I) band normalized water-leaving radiance spectra nLw(λ). The spatial resolutions of the M-band and I-band nLw(λ) are 750 m and 375 m, respectively. With the technique of convolutional neural network (CNN), the M-band nLw(λ) imagery can be super-resolved from 750 m to 375 m spatial resolution by leveraging the high spatial resolution features of I1-band nLw(λ) data. However, it is also important to enhance the spatial resolution of VIIRS-derived chlorophyll-a (Chl-a) concentration and the water diffuse attenuation coefficient at the wavelength of 490 nm (Kd(490)), as well as other biological and biogeochemical products. In this study, we describe our effort to derive high-resolution Kd(490) and Chl-a data based on super-resolved nLw(λ) images at the VIIRS five M-bands. To improve the network performance over extremely turbid coastal oceans and inland waters, the networks are retrained with a training dataset including ocean color data from the Bohai Sea, Baltic Sea, and La Plata River Estuary, covering water types from clear open oceans to moderately turbid and highly turbid waters. The evaluation results show that the super-resolved Kd(490) image is much sharper than the original one, and has more detailed fine spatial structures. A similar enhancement of finer structures is also found in the super-resolved Chl-a images. Chl-a filaments are much sharper and thinner in the super-resolved image, and some of the very fine spatial features that are not shown in the original images appear in the super-resolved Chl-a imageries. The networks are also applied to four other coastal and inland water regions. The results show that super-resolution occurs mainly on pixels of Chl-a and Kd(490) features, especially on the feature edges and locations with a large spatial gradient. The biases between the original M-band images and super-resolved high-resolution images are small for both Chl-a and Kd(490) in moderately to extremely turbid coastal oceans and inland waters, indicating that the super-resolution process does not change the mean values of the original images.

Climate change in the High Mountain Asia simulated with CMIP6 models

2021 ◽  
Author(s):  
Mickaël Lalande ◽  
Martin Ménégoz ◽  
Gerhard Krinner
Keyword(s):  
High Resolution ◽  
Snow Cover ◽  
Climate Models ◽  
Global Climate Models ◽  
Cold Bias ◽  
High Mountain ◽  
The Tibetan Plateau ◽  
Near Surface ◽  
Model Biases ◽  
Snow Cover Extent

<p>The High Mountains of Asia (HMA) region and the Tibetan Plateau (TP), with an average altitude of 4000 m, are hosting the third largest reservoir of glaciers and snow after the two polar ice caps, and are at the origin of strong orographic precipitation. Climate studies over HMA are related to serious challenges concerning the exposure of human infrastructures to natural hazards and the water resources for agriculture, drinking water, and hydroelectricity to whom several hundred million inhabitants of the Indian subcontinent are depending. However, climate variables such as temperature, precipitation, and snow cover are poorly described by global climate models because their coarse resolution is not adapted to the rugged topography of this region. Since the first CMIP exercises, a cold model bias has been identified in this region, however, its attribution is not obvious and may be different from one model to another. Our study focuses on a multi-model comparison of the CMIP6 simulations used to investigate the climate variability in this area to answer the next questions: (1) are the biases in HMA reduced in the new generation of climate models? (2) Do the model biases impact the simulated climate trends? (3) What are the links between the model biases in temperature, precipitation, and snow cover extent? (4) Which climate trajectories can be projected in this area until 2100? An analysis of 27 models over 1979-2014 still show a cold bias in near-surface air temperature over the HMA and TP reaching an annual value of -2.0 °C (± 3.2 °C), associated with an over-extended relative snow cover extent of 53 % (± 62 %), and a relative excess of precipitation of 139 % (± 38 %), knowing that the precipitation biases are uncertain because of the undercatch of solid precipitation in observations. Model biases and trends do not show any clear links, suggesting that biased models should not be excluded in trend and projections analysis, although non-linear effects related to lagged snow cover feedbacks could be expected. On average over 2081-2100 with respect to 1995-2014, for the scenarios SSP126, SSP245, SSP370, and SSP585, the 9 available models shows respectively an increase in annual temperature of 1.9 °C (± 0.5 °C), 3.4 °C (± 0.7 °C), 5.2 °C (± 1.2 °C), and 6.6 °C (± 1.5 °C); a relative decrease in the snow cover extent of 10 % (± 4.1 %), 19 % (± 5 %), 29 % (± 8 %), and 35 % (± 9 %); and an increase in total precipitation of 9 % (± 5 %), 13 % (± 7 %), 19 % (± 11 %), and 27 % (± 13 %). Further analyses will be considered to investigate potential links between the biases at the surface and those at higher tropospheric levels as well as with the topography. The models based on high resolution do not perform better than the coarse-gridded ones, suggesting that the race to high resolution should be considered as a second priority after the developments of more realistic physical parameterizations.</p>

scholarly journals Evapotranspiration Estimation with Small UAVs in Precision Agriculture

Sensors ◽  
2020 ◽  
Vol 20 (22) ◽  
pp. 6427
Author(s):  
Haoyu Niu ◽  
Derek Hollenbeck ◽  
Tiebiao Zhao ◽  
Dong Wang ◽  
YangQuan Chen
Keyword(s):  
Energy Balance ◽  
High Resolution ◽  
Spatial Resolution ◽  
Precision Agriculture ◽  
Large Scale ◽  
Bowen Ratio ◽  
Future Research ◽  
Accurate Estimation ◽  
Research Areas ◽  
Energy Balance Approach

Estimating evapotranspiration (ET) has been one of the most critical research areas in agriculture because of water scarcity, the growing population, and climate change. The accurate estimation and mapping of ET are necessary for crop water management. Traditionally, researchers use water balance, soil moisture, weighing lysimeters, or an energy balance approach, such as Bowen ratio or eddy covariance towers to estimate ET. However, these ET methods are point-specific or area-weighted measurements and cannot be extended to a large scale. With the advent of satellite technology, remote sensing images became able to provide spatially distributed measurements. However, the spatial resolution of multispectral satellite images is in the range of meters, tens of meters, or hundreds of meters, which is often not enough for crops with clumped canopy structures, such as trees and vines. Unmanned aerial vehicles (UAVs) can mitigate these spatial and temporal limitations. Lightweight cameras and sensors can be mounted on the UAVs and take high-resolution images. Unlike satellite imagery, the spatial resolution of the UAV images can be at the centimeter-level. UAVs can also fly on-demand, which provides high temporal imagery. In this study, the authors examined different UAV-based approaches of ET estimation at first. Models and algorithms, such as mapping evapotranspiration at high resolution with internalized calibration (METRIC), the two-source energy balance (TSEB) model, and machine learning (ML) are analyzed and discussed herein. Second, challenges and opportunities for UAVs in ET estimation are also discussed, such as uncooled thermal camera calibration, UAV image collection, and image processing. Then, the authors share views on ET estimation with UAVs for future research and draw conclusive remarks.

scholarly journals An evaluation of the importance of spatial resolution in a global climate and hydrological model based on the Rhine and Mississippi basin

2017 ◽  
Author(s):  
Imme Benedict ◽  
Chiel C. van Heerwaarden ◽  
Albrecht H. Weerts ◽  
Wilco Hazeleger
Keyword(s):  
High Resolution ◽  
Spatial Resolution ◽  
Large Scale ◽  
Climate Models ◽  
Hydrological Cycle ◽  
Global Climate ◽  
Global Scale ◽  
Global Climate Models ◽  
Convective Processes ◽  
Parameter Values

Abstract. The hydrological cycle of river basins can be simulated by combining global climate models (GCMs) and global hydrological models (GHMs). The spatial resolution of these models is restricted by computational resources and therefore limits the processes and level of detail that can be resolved. To further improve simulations of precipitation and river-runoff on a global scale, we assess and compare the benefits of an increased resolution for a GCM and a GHM. We focus on the Rhine and Mississippi basin. Increasing the resolution of a GCM (1.125° to 0.25°) results in more realistic large-scale circulation patterns over the Rhine and an improved precipitation budget. These improvements with increased resolution are not found for the Mississippi basin, most likely because precipitation is strongly dependent on the representation of still unresolved convective processes. Increasing the resolution of vegetation and orography in the high resolution GHM (from 0.5° to 0.05°) shows no significant differences in discharge for both basins, because the hydrological processes depend highly on other parameter values that are not readily available at high resolution. Therefore, increasing the resolution of the GCM provides the most straightforward route to better results. This route works best for basins driven by large-scale precipitation, such as the Rhine basin. For basins driven by convective processes, such as the Mississippi basin, improvements are expected with even higher resolution convection permitting models.

scholarly journals Evaluating Predictor Strategies for Regression-Based Downscaling with a Focus on Glacierized Mountain Environments

2017 ◽  
Vol 56 (6) ◽  
pp. 1707-1729 ◽  
Author(s):  
Marlis Hofer ◽  
Johanna Nemec ◽  
Nicolas J. Cullen ◽  
Markus Weber
Keyword(s):  
Large Scale ◽  
Global Radiation ◽  
Local Scale ◽  
Forecast Skill ◽  
Model Complexity ◽  
High Mountain ◽  
European Alps ◽  
Limited Information ◽  
Mountain Environments ◽  
Measuring Site

AbstractThis study explores the potential of different predictor strategies for improving the performance of regression-based downscaling approaches. The investigated local-scale target variables are precipitation, air temperature, wind speed, relative humidity, and global radiation, all at a daily time scale. Observations of these target variables are assessed from three sites in close proximity to mountain glaciers: 1) the Vernagtbach station in the European Alps, 2) the Artesonraju measuring site in the tropical South American Andes, and 3) the Mount Brewster measuring site in the Southern Alps of New Zealand. The large-scale dataset being evaluated is the ERA-Interim dataset. In the downscaling procedure, particular emphasis is put on developing efficient yet not overfit models from the limited information in the temporally short (typically a few years) observational records of the high mountain sites. For direct (univariate) predictors, optimum scale analysis turns out to be a powerful means to improve the forecast skill without the need to increase the downscaling model complexity. Yet the traditional (multivariate) predictor sets show generally higher skill than the direct predictors for all variables, sites, and days of the year. Only in the case of large sampling uncertainty (identified here to particularly affect observed precipitation) is the use of univariate predictor options justified. Overall, the authors find a range in forecast skill among the different predictor options applied in the literature up to 0.5 (where 0 indicates no skill, and 1 represents perfect skill). This highlights that a sophisticated predictor selection (as presented in this study) is essential in the development of realistic, local-scale scenarios by means of downscaling.

scholarly journals Precipitation Atlas for Germany (GePrA)

Atmosphere ◽  
2019 ◽  
Vol 10 (12) ◽  
pp. 737
Author(s):  
Christopher Jung ◽  
Dirk Schindler
Keyword(s):  
Spatial Resolution ◽  
Large Scale ◽  
High Spatial Resolution ◽  
Spline Interpolation ◽  
Absolute Error ◽  
Coefficient Of Determination ◽  
Small Scale ◽  
Monthly Precipitation ◽  
New Approach ◽  
Very High Spatial Resolution

A new approach for modeling daily precipitation (RR) at very high spatial resolution (25 m × 25 m) was introduced. It was used to develop the Precipitation Atlas for Germany (GePrA). GePrA is based on 2357 RR time series measured in the period 1981–2018. It provides monthly percentiles (p) of the large-scale RR patterns which were mapped by a thin plate spline interpolation (TPS). A least-squares boosting (LSBoost) approach and orographic predictor variables (PV) were applied to integrate the small-scale precipitation variability in GePrA. Then, a Weibull distribution (Wei) was fitted to RRp. It was found that the mean monthly sum of RR ( R R ¯ s u m ) is highest in July (84 mm) and lowest in April (49 mm). A great dependency of RR on the elevation (ε) was found and quantified. Model validation at 425 stations showed a mean coefficient of determination (R2) of 0.80 and a mean absolute error (MAE) of less than 10 mm in all months. The high spatial resolution, including the effects of the local orography, make GePrA a valuable tool for various applications. Since GePrA does not only describe R R ¯ s u m , but also the entire monthly precipitation distributions, the results of this study enable the seasonal differentiation between dry and wet period at small scales.

scholarly journals Probabilistic precipitation and temperature downscaling of the Twentieth Century Reanalysis over France

2016 ◽  
Vol 12 (3) ◽  
pp. 635-662 ◽  
Author(s):  
Laurie Caillouet ◽  
Jean-Philippe Vidal ◽  
Eric Sauquet ◽  
Benjamin Graff
Keyword(s):  
Climate Change ◽  
Twentieth Century ◽  
High Resolution ◽  
Large Scale ◽  
Local Scale ◽  
Precipitation Forecast ◽  
Seasonal Temperature ◽  
Downscaling Method ◽  
Quantitative Precipitation Forecast ◽  
Precipitation And Temperature

Abstract. This work proposes a daily high-resolution probabilistic reconstruction of precipitation and temperature fields in France over the 1871–2012 period built on the NOAA Twentieth Century global extended atmospheric reanalysis (20CR). The objective is to fill in the spatial and temporal data gaps in surface observations in order to improve our knowledge on the local-scale climate variability from the late nineteenth century onwards. The SANDHY (Stepwise ANalogue Downscaling method for HYdrology) statistical downscaling method, initially developed for quantitative precipitation forecast, is used here to bridge the scale gap between large-scale 20CR predictors and local-scale predictands from the Safran high-resolution near-surface reanalysis, available from 1958 onwards only. SANDHY provides a daily ensemble of 125 analogue dates over the 1871–2012 period for 608 climatically homogeneous zones paving France. Large precipitation biases in intermediary seasons are shown to occur in regions with high seasonal asymmetry like the Mediterranean. Moreover, winter and summer temperatures are respectively over- and under-estimated over the whole of France. Two analogue subselection methods are therefore developed with the aim of keeping the structure of the SANDHY method unchanged while reducing those seasonal biases. The calendar selection keeps the analogues closest to the target calendar day. The stepwise selection applies two new analogy steps based on similarity of the sea surface temperature (SST) and the large-scale 2 m temperature (T). Comparisons to the Safran reanalysis over 1959–2007 and to homogenized series over the whole twentieth century show that biases in the interannual cycle of precipitation and temperature are reduced with both methods. The stepwise subselection moreover leads to a large improvement of interannual correlation and reduction of errors in seasonal temperature time series. When the calendar subselection is an easily applicable method suitable in a quantitative precipitation forecast context, the stepwise subselection method allows for potential season shifts and SST trends and is therefore better suited for climate reconstructions and climate change studies. The probabilistic downscaling of 20CR over the period 1871–2012 with the SANDHY probabilistic downscaling method combined with the stepwise subselection thus constitutes a perfect framework for assessing the recent observed meteorological events but also future events projected by climate change impact studies and putting them in a historical perspective.

scholarly journals MADNet 2.0: Pixel-Scale Topography Retrieval from Single-View Orbital Imagery of Mars Using Deep Learning

2021 ◽  
Vol 13 (21) ◽  
pp. 4220
Author(s):  
Yu Tao ◽  
Jan-Peter Muller ◽  
Siting Xiong ◽  
Susan J. Conway
Keyword(s):  
Deep Learning ◽  
High Resolution ◽  
Spatial Resolution ◽  
Large Scale ◽  
Fine Scale ◽  
Martian Surface ◽  
Multi Scale ◽  
Single Scale ◽  
Imaging Science ◽  
Pixel Scale

The High-Resolution Imaging Science Experiment (HiRISE) onboard the Mars Reconnaissance Orbiter provides remotely sensed imagery at the highest spatial resolution at 25–50 cm/pixel of the surface of Mars. However, due to the spatial resolution being so high, the total area covered by HiRISE targeted stereo acquisitions is very limited. This results in a lack of the availability of high-resolution digital terrain models (DTMs) which are better than 1 m/pixel. Such high-resolution DTMs have always been considered desirable for the international community of planetary scientists to carry out fine-scale geological analysis of the Martian surface. Recently, new deep learning-based techniques that are able to retrieve DTMs from single optical orbital imagery have been developed and applied to single HiRISE observational data. In this paper, we improve upon a previously developed single-image DTM estimation system called MADNet (1.0). We propose optimisations which we collectively call MADNet 2.0, which is based on a supervised image-to-height estimation network, multi-scale DTM reconstruction, and 3D co-alignment processes. In particular, we employ optimised single-scale inference and multi-scale reconstruction (in MADNet 2.0), instead of multi-scale inference and single-scale reconstruction (in MADNet 1.0), to produce more accurate large-scale topographic retrieval with boosted fine-scale resolution. We demonstrate the improvements of the MADNet 2.0 DTMs produced using HiRISE images, in comparison to the MADNet 1.0 DTMs and the published Planetary Data System (PDS) DTMs over the ExoMars Rosalind Franklin rover’s landing site at Oxia Planum. Qualitative and quantitative assessments suggest the proposed MADNet 2.0 system is capable of producing pixel-scale DTM retrieval at the same spatial resolution (25 cm/pixel) of the input HiRISE images.

Sign in / Sign up

Export Citation Format

Share Document