scholarly journals CHLOROPHYLL-A CONCENTRATION RETRIEVAL USING CONVOLUTIONAL NEURAL NETWORKS IN LAGUNA LAKE, PHILIPPINES

2019 ◽  
Vol XLII-4/W19 ◽  
pp. 401-405
Author(s):  
M. A. Syariz ◽  
C.-H. Lin ◽  
A. C. Blanco
Keyword(s):  
Neural Networks ◽  
Chlorophyll A ◽  
Convolutional Neural Networks ◽  
Acquisition Time ◽  
Ann Model ◽  
Neural Structure ◽  
Chl A ◽  
Proposed Model ◽  
Laguna Lake

Abstract. Two existing chlorophyll-a (chl-a) concentration retrieval procedures, which are analytical and empirical, are hindered by the complexity in radiative transfer equation (RTE) and in statistical analyses, respectively. Another promising model in this direction is the use of artificial neural networks (ANN). Mostly, a pixel-to-pixel with one-layer ANN model is used; where in fact that the satellite instrumental errors and man-made objects in water bodies might affect the retrieval and should be taken into account. In this study, the mask-based neural structure, called convolutional neural networks (CNN) model containing both the target and neighborhood pixels, is proposed to reduce the influence of the aforementioned premises. The proposed model is an end-to-end multiple-layer model which integrates band expansion, feature extraction, and chl-a estimation into the structure, leading to an optimal chl-a concentration retrieval. In addition to that, a two-stage training is also proposed to solve the problem of insufficient in-situ samples which happens in most of the time. In the first stage, the proposed model is trained by using the chl-a concentration derived from the water product, provided by satellite agency, and is refined with the in-situ samples in the second stage. Eight Sentinel-3 images from different acquisition time and coincide in-situ measurements over Laguna Lake waters of Philippines were utilized to conduct the model training and testing. Based on quantitative accuracy assessment, the proposed method outperformed the existing dual- and triple- bands combinations in chl-a concentration retrieval.

scholarly journals WaterNet: A Convolutional Neural Network for Chlorophyll-a Concentration Retrieval

2020 ◽  
Vol 12 (12) ◽  
pp. 1966 ◽  
Author(s):  
Muhammad Aldila Syariz ◽  
Chao-Hung Lin ◽  
Manh Van Nguyen ◽  
Lalu Muhamad Jaelani ◽  
Ariel C. Blanco
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Neural Networks ◽  
Convolutional Neural Network ◽  
Chlorophyll A ◽  
Remote Sensing Images ◽  
Two Stage ◽  
Chl A ◽  
The Neural Network

The retrieval of chlorophyll-a (Chl-a) concentrations relies on empirical or analytical analyses, which generally experience difficulties from the diversity of inland waters in statistical analyses and the complexity of radiative transfer equations in analytical analyses, respectively. Previous studies proposed the utilization of artificial neural networks (ANNs) to alleviate these problems. However, ANNs do not consider the problem of insufficient in situ samples during model training, and they do not fully utilize the spatial and spectral information of remote sensing images in neural networks. In this study, a two-stage training is introduced to address the problem regarding sample insufficiency. The neural network is pretrained using the samples derived from an existing Chl-a concentration model in the first stage, and the pretrained model is refined with in situ samples in the second stage. A novel convolutional neural network for Chl-a concentration retrieval called WaterNet is proposed which utilizes both spectral and spatial information of remote sensing images. In addition, an end-to-end structure that integrates feature extraction, band expansion, and Chl-a estimation into the neural network leads to an efficient and effective Chl-a concentration retrieval. In experiments, Sentinel-3 images with the same acquisition days of in situ measurements over Laguna Lake in the Philippines were used to train and evaluate WaterNet. The quantitative analyses show that the two-stage training is more likely than the one-stage training to reach the global optimum in the optimization, and WaterNet with two-stage training outperforms, in terms of estimation accuracy, related ANN-based and band-combination-based Chl-a concentration models.

scholarly journals VERTICAL DISTRIBUTION OF CHLOROPHYLL-A BASED ON NEURAL NETWORK

2010 ◽  
Vol 2 (-) ◽  
Author(s):  
TAKAHIRO OSAWA ◽  
CHAO FANG ZHAO ◽  
I WAYAN Nuarsa ◽  
I KETUT SWARDIKA ◽  
YASUHIRO SUGIMORI
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Vertical Distribution ◽  
Primary Production ◽  
Chlorophyll A ◽  
Ocean Color ◽  
Chl A ◽  
In Situ Data ◽  
Artificial Neural

An algorithm of estimating Vertical distribution of Chlorophyll-a (Chl-a) was evaluated based on Artificial Neural Networks (ANN) method in Hokkaido field in the northwest of Pacific Ocean. The algorithm applied to the data of SeaWiFS on OrbView-2 and AVHRR on NOAA off Hokkaido, has been applied on September 24, 1998 and September 28, 2001. Ocean color sensor provides the information of the photosynthetic pigment concentration for the upper 22% of the euphotic zone. In order to model a primary production in the water column derived from satellite, it is important to obtain the vertical profile of Chl-a distribution, because the maximum value of Chl-a concentration used to lie in the subsurface region. A shifted Gaussian model has been proposed to describe the variation of the chlorophyll-a (Chl-a) profile which consists of four parameters, i.e. background biomass (B0), maximum depth of Chl-a (zm), total biomass in the peak (h), and a measurement of the thickness or vertical scale of the peak (cr). However, these parameters are not easy to be determined directly from satellite data. Therefore, in the present study, an ANN methodology is used. Using in-situ data from 1974 to 1994 around Japan Islands, the above four parameters are calculated to derive the Chl-a concentration, sea surface temperature, mixed layer depth, latitude, longitude, and Julian days. The total of 6983 profiles of Chl-a and temperature are used for ANN. The correlation coefficients of these parameters are 0.79 (B0), 0.73 (h), 0.76 (cr) and 0.79 (zm) respectively. A site called A-linc off Hokkaido is used to evaluate Chl-a concentration in each depth. After comparing with in-situ data and ANN model, the results show good agreement relatively. Therefore, the ANN method is applicable and available tool to estimate primary production and fish resources from the space. Keywords : Ocean color, Chlorophyll-a (Chl-a), Vertical structure, Artificial Neural Networks (ANN).

scholarly journals Temporal Variation of Chlorophyll-a Concentrations in Highly Dynamic Waters from Unattended Sensors and Remote Sensing Observations

Sensors ◽  
2018 ◽  
Vol 18 (8) ◽  
pp. 2699 ◽  
Author(s):  
Jian Li ◽  
Liqiao Tian ◽  
Qingjun Song ◽  
Zhaohua Sun ◽  
Hongjing Yu ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Water Quality ◽  
Chlorophyll Fluorescence ◽  
Chlorophyll A ◽  
Temporal Variations ◽  
Lake Area ◽  
Short Term ◽  
Chl A ◽  
Spatio Temporal

Monitoring of water quality changes in highly dynamic inland lakes is frequently impeded by insufficient spatial and temporal coverage, for both field surveys and remote sensing methods. To track short-term variations of chlorophyll fluorescence and chlorophyll-a concentrations in Poyang Lake, the largest freshwater lake in China, high-frequency, in-situ, measurements were collected from two fixed stations. The K-mean clustering method was also applied to identify clusters with similar spatio-temporal variations, using remote sensing Chl-a data products from the MERIS satellite, taken from 2003 to 2012. Four lake area classes were obtained with distinct spatio-temporal patterns, two of which were selected for in situ measurement. Distinct daily periodic variations were observed, with peaks at approximately 3:00 PM and troughs at night or early morning. Short-term variations of chlorophyll fluorescence and Chl-a levels were revealed, with a maximum intra-diurnal ratio of 5.1 and inter-diurnal ratio of 7.4, respectively. Using geostatistical analysis, the temporal range of chlorophyll fluorescence and corresponding Chl-a variations was determined to be 9.6 h, which indicates that there is a temporal discrepancy between Chl-a variations and the sampling frequency of current satellite missions. An analysis of the optimal sampling strategies demonstrated that the influence of the sampling time on the mean Chl-a concentrations observed was higher than 25%, and the uncertainty of any single Terra/MODIS or Aqua/MODIS observation was approximately 15%. Therefore, sampling twice a day is essential to resolve Chl-a variations with a bias level of 10% or less. The results highlight short-term variations of critical water quality parameters in freshwater, and they help identify specific design requirements for geostationary earth observation missions, so that they can better address the challenges of monitoring complex coastal and inland environments around the world.

scholarly journals Stock Pattern Classification from Charts using Deep Learning Algorithms

2020 ◽  
Vol 3 (1) ◽  
pp. 445-454
Author(s):  
Celal Buğra Kaya ◽  
Alperen Yılmaz ◽  
Gizem Nur Uzun ◽  
Zeynep Hilal Kilimci
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Pattern Classification ◽  
Short Term Memory ◽  
Stock Exchange ◽  
Learning Techniques ◽  
Proposed Model ◽  
Istanbul Stock Exchange

Pattern classification is related with the automatic finding of regularities in dataset through the utilization of various learning techniques. Thus, the classification of the objects into a set of categories or classes is provided. This study is undertaken to evaluate deep learning methodologies to the classification of stock patterns. In order to classify patterns that are obtained from stock charts, convolutional neural networks (CNNs), recurrent neural networks (RNNs), and long-short term memory networks (LSTMs) are employed. To demonstrate the efficiency of proposed model in categorizing patterns, hand-crafted image dataset is constructed from stock charts in Istanbul Stock Exchange and NASDAQ Stock Exchange. Experimental results show that the usage of convolutional neural networks exhibits superior classification success in recognizing patterns compared to the other deep learning methodologies.

scholarly journals SATELLITE-DERIVED BATHYMETRY USING CONVOLUTIONAL NEURAL NETWORKS AND MULTISPECTRAL SENTINEL-2 IMAGES

2021 ◽  
Vol XLIII-B3-2021 ◽  
pp. 201-207
Author(s):  
Y. A. Lumban-Gaol ◽  
K. A. Ohori ◽  
R. Y. Peters
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Window Size ◽  
Short Wave ◽  
Training Data ◽  
Coefficient Of Determination ◽  
Linear Transform ◽  
Band Combinations ◽  
Sentinel 2

Abstract. Satellite-Derived Bathymetry (SDB) has been used in many applications related to coastal management. SDB can efficiently fill data gaps obtained from traditional measurements with echo sounding. However, it still requires numerous training data, which is not available in many areas. Furthermore, the accuracy problem still arises considering the linear model could not address the non-relationship between reflectance and depth due to bottom variations and noise. Convolutional Neural Networks (CNN) offers the ability to capture the connection between neighbouring pixels and the non-linear relationship. These CNN characteristics make it compelling to be used for shallow water depth extraction. We investigate the accuracy of different architectures using different window sizes and band combinations. We use Sentinel-2 Level 2A images to provide reflectance values, and Lidar and Multi Beam Echo Sounder (MBES) datasets are used as depth references to train and test the model. A set of Sentinel-2 and in-situ depth subimage pairs are extracted to perform CNN training. The model is compared to the linear transform and applied to two other study areas. Resulting accuracy ranges from 1.3 m to 1.94 m, and the coefficient of determination reaches 0.94. The SDB model generated using a window size of 9x9 indicates compatibility with the reference depths, especially at areas deeper than 15 m. The addition of both short wave infrared bands to the four visible bands in training improves the overall accuracy of SDB. The implementation of the pre-trained model to other study areas provides similar results depending on the water conditions.

Time Series Based House Sale Value Market Forecasting Using Genetically Evolved Neural Networks

2010 ◽  
pp. 265-282
Author(s):  
George S. Atsalakis ◽  
Kimon P. Valavanis ◽  
Constantin Zopounidis ◽  
Dimitris Nezis
Keyword(s):  
Neural Networks ◽  
Linear Regression ◽  
Mean Square Error ◽  
Fuzzy Inference ◽  
Housing Prices ◽  
Individual Investors ◽  
Mean Square ◽  
Ann Model ◽  
Neuro Fuzzy ◽  
Proposed Model

Accurate forecasting of the house sale value market is important for individual investors, business investors, banks and mortgage companies. This chapter uses fundamentals of Genetic Algorithms (GAs) and Artificial Neural Networks (ANNs) to derive and implement a hybrid, genetically evolved feedforward ANN model that predicts next month house sale prices. Derived model results are compared with results obtained using a linear regression model and an Adaptive Neuro Fuzzy Inference System (ANFIS). The proposed model returned lower Root Mean Square Error (RMSE), Absolute Mean Error (MAE), Mean Square Error (MSE) and Mean Absolute Percent Error (MAPE) results compared with the linear regression and ANFIS models. For case studies real monthly data of USA housing prices from 1963 to 2007 were used.

scholarly journals Auditory Inspired Convolutional Neural Networks for Ship Type Classification with Raw Hydrophone Data

Entropy ◽  
2018 ◽  
Vol 20 (12) ◽  
pp. 990 ◽  
Author(s):  
Sheng Shen ◽  
Honghui Yang ◽  
Junhao Li ◽  
Guanghui Xu ◽  
Meiping Sheng
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Filter Banks ◽  
Auditory Filter ◽  
Feature Representations ◽  
Proposed Model ◽  
Energy Pooling ◽  
Practical Guidelines ◽  
Frequency Components ◽  
Underwater Acoustic Signal

Detecting and classifying ships based on radiated noise provide practical guidelines for the reduction of underwater noise footprint of shipping. In this paper, the detection and classification are implemented by auditory inspired convolutional neural networks trained from raw underwater acoustic signal. The proposed model includes three parts. The first part is performed by a multi-scale 1D time convolutional layer initialized by auditory filter banks. Signals are decomposed into frequency components by convolution operation. In the second part, the decomposed signals are converted into frequency domain by permute layer and energy pooling layer to form frequency distribution in auditory cortex. Then, 2D frequency convolutional layers are applied to discover spectro-temporal patterns, as well as preserve locality and reduce spectral variations in ship noise. In the third part, the whole model is optimized with an objective function of classification to obtain appropriate auditory filters and feature representations that are correlative with ship categories. The optimization reflects the plasticity of auditory system. Experiments on five ship types and background noise show that the proposed approach achieved an overall classification accuracy of 79.2%, which improved by 6% compared to conventional approaches. Auditory filter banks were adaptive in shape to improve accuracy of classification.

Detection of Carolina Geranium (Geranium carolinianum) Growing in Competition with Strawberry Using Convolutional Neural Networks

Weed Science ◽  
2018 ◽  
Vol 67 (2) ◽  
pp. 239-245 ◽  
Author(s):  
Shaun M. Sharpe ◽  
Arnold W. Schumann ◽  
Nathan S. Boyd
Keyword(s):  
Neural Networks ◽  
Image Classification ◽  
Convolutional Neural Networks ◽  
Future Research ◽  
Study Objective ◽  
Weed Interference ◽  
Detection Technology ◽  
Optimal Approach ◽  
In Situ Detection

AbstractWeed interference during crop establishment is a serious concern for Florida strawberry [Fragaria×ananassa(Weston) Duchesne ex Rozier (pro sp.) [chiloensis×virginiana]] producers. In situ remote detection for precision herbicide application reduces both the risk of crop injury and herbicide inputs. Carolina geranium (Geranium carolinianumL.) is a widespread broadleaf weed within Florida strawberry production with sensitivity to clopyralid, the only available POST broadleaf herbicide.Geranium carolinianumleaf structure is distinct from that of the strawberry plant, which makes it an ideal candidate for pattern recognition in digital images via convolutional neural networks (CNNs). The study objective was to assess the precision of three CNNs in detectingG. carolinianum. Images ofG. carolinianumgrowing in competition with strawberry were gathered at four sites in Hillsborough County, FL. Three CNNs were compared, including object detection–based DetectNet, image classification–based VGGNet, and GoogLeNet. Two DetectNet networks were trained to detect either leaves or canopies ofG. carolinianum. Image classification using GoogLeNet and VGGNet was largely unsuccessful during validation with whole images (Fscore<0.02). CNN training using cropped images increasedG. carolinianumdetection during validation for VGGNet (Fscore=0.77) and GoogLeNet (Fscore=0.62). TheG. carolinianumleaf–trained DetectNet achieved the highestFscore(0.94) for plant detection during validation. Leaf-based detection led to more consistent detection ofG. carolinianumwithin the strawberry canopy and reduced recall-related errors encountered in canopy-based training. The smaller target of leaf-based DetectNet did increase false positives, but such errors can be overcome with additional training images for network desensitization training. DetectNet was the most viable CNN tested for image-based remote sensing ofG. carolinianumin competition with strawberry. Future research will identify the optimal approach for in situ detection and integrate the detection technology with a precision sprayer.

Sign in / Sign up

Export Citation Format

Share Document