HR-SAR-Net: A Deep Neural Network for Urban Scene Segmentation from High-Resolution SAR Data

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.

Download Full-text

Rate-Based Decoding of Images from Multi-Region, High Resolution, Electrode Recordings In the Mouse Visual System

10.1101/2021.07.07.451504 ◽

2021 ◽

Author(s):

Christopher B Fritz

Keyword(s):

Neural Network ◽

High Resolution ◽

Neural Activity ◽

Deep Neural Network ◽

Superior Performance ◽

Brain Machine Interface ◽

Feed Forward ◽

Deep Networks ◽

Feed Forward Neural Networks ◽

Machine Interface

We hypothesize that deep networks are superior to linear decoders at recovering visual stimuli from neural activity. Using high-resolution, multielectrode Neuropixels recordings, we verify this is the case for a simple feed-forward deep neural network having just 7 layers. These results suggest that these feed-forward neural networks and perhaps more complex deep architectures will give superior performance in a visual brain-machine interface.

Download Full-text

High-resolution soil moisture retrieval using a Neural Network approach from Sentinel-1 SAR data

10.5194/egusphere-egu2020-9995 ◽

2020 ◽

Author(s):

Qi Gao ◽

Maria Jose Escorihuela ◽

Nemesio Rodriguez-Fernandez ◽

Olivier Merlin ◽

Mehrez Zribi

Keyword(s):

Neural Network ◽

Soil Moisture ◽

High Resolution ◽

Neural Network Training ◽

Neural Network Approach ◽

Auxiliary Data ◽

Network Training ◽

The Neural Network ◽

Sar Data

High-resolution soil moisture product is important for agriculture-related managements including irrigation. We have investigated the Change Detection (CD) method using Sentinel-1 data for 100 m resolution soil moisture retrieval and got a Root Mean Square Error (RMSE) about 0.6 m3/m3. However, the result of this approach is not accurate enough for high-density crops like corn. Another approach needs to be studied to get better accuracy over all types of crops. The artificial neural network (NN) technique, which involves nonlinear parameterized mapping from an input vector to an output vector, is an appropriate tool for retrieving geophysical parameters from remote sensing data. Many studies have explored the NN approach for processing remotely sensed data, including retrieving soil moisture, however, only a few studies [Notarnicola et al., 2010; Paloscia et al., 2013, etc.] had investigated NN for soil moisture estimation over vegetation-covered areas, especially in a large scale.The objective of this study is to develop an approach based on neural networks to estimate soil moisture at high resolution over vegetation-covered areas from Sentinel-1 C-band SAR data. The quality of the output results depends directly on the quality of the input data used to train the NN and the reference data for the training, therefore, we performed our study over Catalonia, where we have many auxiliary data. The study is performed using both VV and VH polarization over the whole Catalonia. Apart from Sentinel-1 SAR data, auxiliary data including Sentinel-2 NDVI, SMAP soil moisture, CCI (ESA Climate Change Initiative) land cover, SIGPAC (Sistema de Informaci&#243;n Geogr&#225;fica de Parcelas Agr&#237;colas) land cover, irrigation index and crop type information from SIGPAC, and DEM (Digital elevation model) are also used for approach development. DISPATCH (Disaggregation based on Physical and Theoretical scale Change) soil moisture product at 1 km resolution is considered as the target in the Neural Network training, adding great value to our study. To prepare the Neural Network training, all data sets are co-registered at 1 km resolution within the same size and resampled for the same dates within one year (2017). Two indexes describing the normalized backscatter difference and soil moisture are introduced as equation (1) and (2):<table><tbody><tr><td>Index1 = (&#963;0i - &#963;0min) / (&#963;0max - &#963;0min)</td> <td>(1)</td> </tr><tr><td>Index2 = SMmin + (SMmax - SMmin) * Index1</td> <td>(2)</td> </tr></tbody></table>&#160;Different parameters were tested to train the Neural Network approach, the preliminary results show a correlation value compared with DISPATCH product about 0.71 over croplands, 0.73 over irrigated fields, and 0.65 over forests, considering Index1, Index2 and SMAP soil moisture. Works are still on-going to try to improve the results by better analyzing the SAR data performance over different fields and conditions. The final goal of the study is to produce 100 m resolution soil moisture product. After 1 km resolution study, we will apply the approach at 100m resolution, and the in-situ soil moisture will be used for validation.This work is inscribed within the Water4Ever project, which is funded by the European Commission under the framework of the ERA-NET COFUND WATERWORKS 2015 Programme.&#160;

Download Full-text