scholarly journals A Convolutional Neural Network for Spatial Downscaling of Satellite-Based Solar-Induced Chlorophyll Fluorescence (SIFnet)

2021 ◽  
Author(s):  
Johannes Gensheimer ◽  
Alexander Jay Turner ◽  
Philipp Köhler ◽  
Christian Frankenberg ◽  
Jia Chen
Keyword(s):  
Neural Network ◽  
United States ◽  
Chlorophyll Fluorescence ◽  
Convolutional Neural Network ◽  
Spatial Resolution ◽  
Vegetation Index ◽  
Spatial Scales ◽  
The United States ◽  
Cycle Space ◽  
Auxiliary Data

Abstract. Gross primary productivity (GPP) is the sum of leaf photosynthesis and represents a crucial component of the global carbon cycle. Space-borne estimates of GPP typically rely on observable quantities that co-vary with GPP such as vegetation indices using reflectance measurements (e.g., NDVI, NIRv, and kNDVI). Recent work has also utilized measurements of solar-induced chlorophyll fluorescence (SIF) as a proxy for GPP. However, these SIF measurements are typically coarse resolution while many processes influencing GPP occur at fine spatial scales. Here, we develop a Convolutional Neural Network (CNN), named SIFnet, that increases the resolution of SIF from the TROPOspheric Monitoring Instrument (TROPOMI) on board of the satellite Sentinel-5P by a factor of 10 to a spatial resolution of 500 m. SIFnet utilizes coarse SIF observations together with high resolution auxiliary data. The auxiliary data used here may carry information related to GPP and SIF. We use training data from non-US regions between April 2018 until March 2021 and evaluate our CNN over the conterminous United States (CONUS). We show that SIFnet is able to increase the resolution of TROPOMI SIF by a factor of 10 with a r2 and RMSE metrics of 0.92 and 0.17 mW m−2 sr−1 nm−1, respectively. We further compare SIFnet against a recently developed downscaling approach and evaluate both methods against independent SIF measurements from Orbiting Carbon Observatory 2 and 3 (OCO-2/3). SIFnet performs systematically better than the downscaling approach (r = 0.78 for SIFnet, r = 0.72 for downscaling), indicating that it is picking up on key features related to SIF and GPP. Examination of the feature importance in the neural network indicates a few key parameters and the spatial regions these parameters matter. Namely, the CNN finds low resolution SIF data to be the most significant parameter with the NIRv vegetation index as the second most important parameter. NIRv consistently outperforms the recently proposed kNDVI vegetation index. Advantages and limitations of SIFnet are investigated and presented through a series of case studies across the United States. SIFnet represents a robust method to infer continuous, high spatial resolution SIF data.

scholarly journals Building Extraction at Scale Using Convolutional Neural Network: Mapping of the United States

2018 ◽  
Vol 11 (8) ◽  
pp. 2600-2614 ◽  
Author(s):  
Hsiuhan Lexie Yang ◽  
Jiangye Yuan ◽  
Dalton Lunga ◽  
Melanie Laverdiere ◽  
Amy Rose ◽  
...  
Keyword(s):  
Neural Network ◽  
United States ◽  
Convolutional Neural Network ◽  
The United States ◽  
Building Extraction ◽  
Network Mapping

scholarly journals Predicting road quality using high resolution satellite imagery: A transfer learning approach

PLoS ONE ◽  
2021 ◽  
Vol 16 (7) ◽  
pp. e0253370
Author(s):  
Ethan Brewer ◽  
Jason Lin ◽  
Peter Kemper ◽  
John Hennin ◽  
Dan Runfola
Keyword(s):  
Neural Network ◽  
United States ◽  
Convolutional Neural Network ◽  
Transfer Learning ◽  
Satellite Imagery ◽  
The United States ◽  
Accurate Information ◽  
Learning Approach ◽  
Road Infrastructure ◽  
Health And Economic Development

Recognizing the importance of road infrastructure to promote human health and economic development, actors around the globe are regularly investing in both new roads and road improvements. However, in many contexts there is a sparsity—or complete lack—of accurate information regarding existing road infrastructure, challenging the effective identification of where investments should be made. Previous literature has focused on overcoming this gap through the use of satellite imagery to detect and map roads. In this piece, we extend this literature by leveraging satellite imagery to estimate road quality and concomitant information about travel speed. We adopt a transfer learning approach in which a convolutional neural network architecture is first trained on data collected in the United States (where data is readily available), and then “fine-tuned” on an independent, smaller dataset collected from Nigeria. We test and compare eight different convolutional neural network architectures using a dataset of 53,686 images of 2,400 kilometers of roads in the United States, in which each road segment is measured as “low”, “middle”, or “high” quality using an open, cellphone-based measuring platform. Using satellite imagery to estimate these classes, we achieve an accuracy of 80.0%, with 99.4% of predictions falling within the actual or an adjacent class. The highest performing base model was applied to a preliminary case study in Nigeria, using a dataset of 1,000 images of paved and unpaved roads. By tailoring our US-model on the basis of this Nigeria-specific data, we were able to achieve an accuracy of 94.0% in predicting the quality of Nigerian roads. A continuous case estimate also showed the ability, on average, to predict road quality to within 0.32 on a 0 to 3 scale (with higher values indicating higher levels of quality).

scholarly journals Klasifikasi Citra Pigmen Kanker Kulit Menggunakan Convolutional Neural Network

2021 ◽  
Vol 5 (2) ◽  
pp. 379-385
Author(s):  
Luqman Hakim ◽  
Zamah Sari ◽  
Handhajani Handhajani
Keyword(s):  
Neural Network ◽  
United States ◽  
Neural Networks ◽  
Skin Cancer ◽  
Convolutional Neural Network ◽  
The United States ◽  
Skin Imaging ◽  
Test And Evaluation ◽  
Skin Cancers ◽  
Fully Connected

Skin cancer is a very common form of cancer that can be found in the United States with annual treatment costs exceeding $ 8 billion. New innovations in the classification and detection of skin cancer using artificial neural networks continue to develop to help the medical and medical world in analyzing images accurately and accurately. Researchers propose to classify skin cancer pigments by focusing on two classes, namely non-melanocytic malignant and benign, where the skin cancer category which is classified into the non-melanocytic class is Actinic keratoses, Basal cell carcinoma. While skin cancers that are classified into Benign are Benign keratosis like lesions, dermatofibrama, vascular lessions. The method used in this study is Convolutional Neural Network (CNN) with a model architecture using 8 Convolutional 2D layers which have filters (16, 16, 32, 32, 64, 64, 128, 128). The first input layers are (20,20). and the following layers (5,5 and 3,3), the types of pooling used in this study are MaxPooling and AveragePooling. The Fully Connected Layer used is (256, 128) and uses a Dropout (0.2). The dataset is obtained from the International Skin Imaging Collaboration (ISIC) 2018 with a total of 10015 images. Based on the results of the test and evaluation reports, an accuracy of 75% is obtained. with the highest precision and recall values ​​found in the Benign class, namely 0.80 and 0.82 respectively and the f1_score value of 0.81.  

scholarly journals Method for Mapping Rice Fields in Complex Landscape Areas Based on Pre-Trained Convolutional Neural Network from HJ-1 A/B Data

2018 ◽  
Vol 7 (11) ◽  
pp. 418 ◽  
Author(s):  
Tian Jiang ◽  
Xiangnan Liu ◽  
Ling Wu
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Time Series ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Vegetation Index ◽  
Southern China ◽  
Series Data ◽  
Support Vector ◽  
Complex Landscape

Accurate and timely information about rice planting areas is essential for crop yield estimation, global climate change and agricultural resource management. In this study, we present a novel pixel-level classification approach that uses convolutional neural network (CNN) model to extract the features of enhanced vegetation index (EVI) time series curve for classification. The goal is to explore the practicability of deep learning techniques for rice recognition in complex landscape regions, where rice is easily confused with the surroundings, by using mid-resolution remote sensing images. A transfer learning strategy is utilized to fine tune a pre-trained CNN model and obtain the temporal features of the EVI curve. Support vector machine (SVM), a traditional machine learning approach, is also implemented in the experiment. Finally, we evaluate the accuracy of the two models. Results show that our model performs better than SVM, with the overall accuracies being 93.60% and 91.05%, respectively. Therefore, this technique is appropriate for estimating rice planting areas in southern China on the basis of a pre-trained CNN model by using time series data. And more opportunity and potential can be found for crop classification by remote sensing and deep learning technique in the future study.

scholarly journals Global downscaling of remotely sensed soil moisture using neural networks

2018 ◽  
Vol 22 (10) ◽  
pp. 5341-5356 ◽  
Author(s):  
Seyed Hamed Alemohammad ◽  
Jana Kolassa ◽  
Catherine Prigent ◽  
Filipe Aires ◽  
Pierre Gentine
Keyword(s):  
Soil Moisture ◽  
Spatial Resolution ◽  
Land Surface ◽  
Vegetation Index ◽  
Spatial Scales ◽  
Ancillary Data ◽  
Repeat Time ◽  
Spatiotemporal Scales ◽  
Better Than

Abstract. Characterizing soil moisture at spatiotemporal scales relevant to land surface processes (i.e., of the order of 1 km) is necessary in order to quantify its role in regional feedbacks between the land surface and the atmospheric boundary layer. Moreover, several applications such as agricultural management can benefit from soil moisture information at fine spatial scales. Soil moisture estimates from current satellite missions have a reasonably good temporal revisit over the globe (2–3-day repeat time); however, their finest spatial resolution is 9 km. NASA's Soil Moisture Active Passive (SMAP) satellite has estimated soil moisture at two different spatial scales of 36 and 9 km since April 2015. In this study, we develop a neural-network-based downscaling algorithm using SMAP observations and disaggregate soil moisture to 2.25 km spatial resolution. Our approach uses the mean monthly Normalized Differenced Vegetation Index (NDVI) as ancillary data to quantify the subpixel heterogeneity of soil moisture. Evaluation of the downscaled soil moisture estimates against in situ observations shows that their accuracy is better than or equal to the SMAP 9 km soil moisture estimates.

scholarly journals Nature inequity and higher COVID-19 case rates in less-green neighbourhoods in the United States

2021 ◽  
Author(s):  
Erica N. Spotswood ◽  
Matthew Benjamin ◽  
Lauren Stoneburner ◽  
Megan M. Wheeler ◽  
Erin E. Beller ◽  
...  
Keyword(s):  
United States ◽  
Low Income ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
The United States ◽  
Incidence Rates ◽  
Lower Income ◽  
Urban Nature ◽  
Urbanized Areas ◽  
Block Groups

AbstractUrban nature—such as greenness and parks—can alleviate distress and provide space for safe recreation during the COVID-19 pandemic. However, nature is often less available in low-income populations and communities of colour—the same communities hardest hit by COVID-19. In analyses of two datasets, we quantified inequity in greenness and park proximity across all urbanized areas in the United States and linked greenness and park access to COVID-19 case rates for ZIP codes in 17 states. Areas with majority persons of colour had both higher case rates and less greenness. Furthermore, when controlling for sociodemographic variables, an increase of 0.1 in the Normalized Difference Vegetation Index was associated with a 4.1% decrease in COVID-19 incidence rates (95% confidence interval: 0.9–6.8%). Across the United States, block groups with lower income and majority persons of colour are less green and have fewer parks. Our results demonstrate that the communities most impacted by COVID-19 also have the least nature nearby. Given that urban nature is associated with both human health and biodiversity, these results have far-reaching implications both during and beyond the pandemic.

scholarly journals Fine-Scale Population Genetic Structure and Within-Tree Distribution of Mating Types of Venturia effusa, Cause of Pecan Scab in the United States

2018 ◽  
Vol 108 (11) ◽  
pp. 1326-1336 ◽  
Author(s):  
Clive H. Bock ◽  
Carolyn A. Young ◽  
Katherine L. Stevenson ◽  
Nikki D. Charlton
Keyword(s):  
United States ◽  
Genetic Diversity ◽  
Asexual Reproduction ◽  
Population Genetic ◽  
Spatial Scales ◽  
The United States ◽  
Source Population ◽  
Mating Types ◽  
Fine Scale ◽  
Scale Population

Scab (caused by Venturia effusa) is the major disease of pecan in the southeastern United States. There is no information available on the fine-scale population genetic diversity or the occurrence of clonal types at small spatial scales that provides insight into inoculum sources and dispersal mechanisms, and potential opportunity for sexual reproduction. To investigate fine-scale genetic diversity, four trees of cultivar Wichita (populations) were sampled hierarchically: within each tree canopy, four approximately evenly spaced terminals (subpopulations) were selected and up to six leaflets (sub-subpopulations) were sampled from different compound leaves on each terminal. All lesions (n = 1 to 8) on each leaflet were sampled. The isolates were screened against a panel of 29 informative microsatellite markers and the resulting multilocus genotypes (MLG) subject to analysis. Mating type was also determined for each isolate. Of 335 isolates, there were 165 MLG (clonal fraction 49.3%). Nei’s unbiased measure of genetic diversity for the clone-corrected data were moderate to high (0.507). An analysis of molecular variance demonstrated differentiation (P = 0.001) between populations on leaflets within individual terminals and between terminals within trees in the tree canopies, with 93.8% of variance explained among isolates within leaflet populations. Other analyses (minimum-spanning network, Bayesian, and discriminant analysis of principal components) all indicated little affinity of isolate for source population. Of the 335 isolates, most unique MLG were found at the stratum of the individual leaflets (n = 242), with similar total numbers of unique MLG observed at the strata of the terminal (n = 170), tree (n = 166), and orchard (n = 165). Thus, the vast majority of shared clones existed on individual leaflets on a terminal at the scale of 10s of centimeters or less, indicating a notable component of short-distance dispersal. There was significant linkage disequilibrium (P < 0.001), and an analysis of Psex showed that where there were multiple encounters of an MLG, they were most probably the result of asexual reproduction (P < 0.05) but there was no evidence that asexual reproduction was involved in single or first encounters of an MLG (P > 0.05). Overall, the MAT1-1-1 and MAT1-2-1 idiomorphs were at equilibrium (73:92) and in most populations, subpopulations, and sub-subpopulations. Both mating types were frequently observed on the same leaflet. The results provide novel information on the characteristics of populations of V. effusa at fine spatial scales, and provide insights into the dispersal of the organism within and between trees. The proximity of both mating idiomorphs on single leaflets is further evidence of opportunity for development of the sexual stage in the field.

DNA-based quantification of Fusarium oxysporum f. sp. vasinfectum in environmental soils to describe spatial variation in inoculum density

Plant Disease ◽  
2022 ◽  
Author(s):  
Roy Davis ◽  
Thomas Isakeit ◽  
Thomas Chappell
Keyword(s):  
United States ◽  
Fusarium Oxysporum ◽  
Spatial Scales ◽  
The United States ◽  
Inoculum Density ◽  
Root Knot Nematode ◽  
West Texas ◽  
Sudden Appearance ◽  
Digital Polymerase Chain Reaction ◽  
Race 4

Fusarium wilt of cotton, caused by the soilborne fungal pathogen Fusarium oxysporum f. sp. vasinfectum (FOV), occurs in regions of the United States where cotton (Gossypium spp.) is grown. Race 4 of this pathogen (FOV4) is especially aggressive and does not require the co-occurrence of the root knot nematode (Meloidogyne incognita) to infect cotton. Its sudden appearance in far-west Texas in 2016 after many years of being restricted to California is of great concern, as is the threat of its continued spread through the cotton-producing regions of the United States. The aim of this research was to analyze the spatial variability of FOV4 inoculum density in the location where FOV4 is locally emerging, using quantitative and droplet digital polymerase chain reaction (qPCR and ddPCR) methods. Soil samples collected from a field with known FOV4 incidence in Fabens, Texas were analyzed. Appreciable variation in inoculum density was found to occur at spatial scales smaller than the size of plots involved in cultivar trial research, and was spatially autocorrelated (Moran’s I, Z = 17.73, p < 0.0001). These findings indicate that for cultivar trials, accounting for the spatial distribution of inoculum either by directly quantifying it or through the use of densely-distributed “calibration checks” is important to the interpretation of results.

scholarly journals Remote Sensing Landslide Recognition Based on Convolutional Neural Network

2019 ◽  
Vol 2019 ◽  
pp. 1-12 ◽  
Author(s):  
Yu Wang ◽  
Xiaofei Wang ◽  
Junfan Jian
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Convolutional Neural Network ◽  
Large Scale ◽  
Vegetation Index ◽  
Near Infrared ◽  
Spatial Information ◽  
Spectral Characteristics ◽  
Remote Sensing Images ◽  
Landslide Event

Landslides are a type of frequent and widespread natural disaster. It is of great significance to extract location information from the landslide in time. At present, most articles still select single band or RGB bands as the feature for landslide recognition. To improve the efficiency of landslide recognition, this study proposed a remote sensing recognition method based on the convolutional neural network of the mixed spectral characteristics. Firstly, this paper tried to add NDVI (normalized difference vegetation index) and NIRS (near-infrared spectroscopy) to enhance the features. Then, remote sensing images (predisaster and postdisaster images) with same spatial information but different time series information regarding landslide are taken directly from GF-1 satellite as input images. By combining the 4 bands (red + green + blue + near-infrared) of the prelandslide remote sensing images with the 4 bands of the postlandslide images and NDVI images, images with 9 bands were obtained, and the band values reflecting the changing characteristics of the landslide were determined. Finally, a deep learning convolutional neural network (CNN) was introduced to solve the problem. The proposed method was tested and verified with remote sensing data from the 2015 large-scale landslide event in Shanxi, China, and 2016 large-scale landslide event in Fujian, China. The results showed that the accuracy of the method was high. Compared with the traditional methods, the recognition efficiency was improved, proving the effectiveness and feasibility of the method.

Sign in / Sign up

Export Citation Format

Share Document