A neural network correlator for satellite imagery and ground truth data in a geographical information system

1991 ◽  
Author(s):  
X. Wu ◽  
J. Westervelt
Keyword(s):  
Neural Network ◽  
Information System ◽  
Geographical Information System ◽  
Satellite Imagery ◽  
Ground Truth ◽  
Geographical Information ◽  
Ground Truth Data

scholarly journals Data Note: COVID-19, social distancing, and pipeline vandalism in Nigeria

F1000Research ◽  
2021 ◽  
Vol 10 ◽  
pp. 604
Author(s):  
P. N. Onwuachi-Iheagwara ◽  
B.I Iheagwara
Keyword(s):  
Information System ◽  
Geographical Information System ◽  
Satellite Imagery ◽  
Historical Data ◽  
Geographical Information ◽  
Port Harcourt ◽  
Group A ◽  
One Year ◽  
Group B ◽  
Group D

We present a dataset of the monthly cases of pipeline vandalism in Nigeria from January 2015 to January 2021. Data used in this study were collated from the Monthly Financial and Operations Reports (MFOR) of the Nigeria National Petroleum Corporation (NNPC). Each MFOR provides cases of pipeline vandalism during a 12-month span from five key locations; Mosimi, Kaduna, Port Harcourt, Warri, and Gombe. Recorded incidences of pipeline vandalism from these locations were summed and assembled into five groups; namely: historical data, prior-COVID-19, COVID-19 lockdown, and post-COVID-19 lockdown. The data were grouped based on dates. These dates were January 2015 to July 2019, August 2019 to January 2020, February 2020 to July 2020, and August 2020 to January 2021 respectively. The historical data were further sub-divided into four sub-groups based on the deployment (May 2016) of sophisticated weapons, satellite imagery, and geographical information system into the security apparatus to checkmate pipeline vandalism. The four sub-groups are sub-group A (one-year before deployment), sub-group B (the year of deployment), sub-group C (one-year after deployment), and sub-group D (two-years after deployment). The dates span for each sub-group is May 2015-April 2016, May 2016-April 2017, May 2017-April 2018, and May 2018-April 2019 respectively. After the deployment of GIS devices in May 2016, the accumulated national number of pipeline vandalism cases declined from 400 cases in January 2016 to 293 in February 2016, and 259 cases in March 2016 as opposed to 60, 49, and 94 cases in the same months in 2017; but over the years, 2017 to 2021 these methods have proved less effective, and cases of pipeline vandalism have risen once more. Similar changes in the number of cases and patterns were observed during the COVID-19 movement restrictions. From the dataset, it can be seen that COVID-19 influenced incidences of pipeline vandalism.

scholarly journals Spatio-Temporal Modeling of Ozone Distribution in Tehran, Iran Based on Neural Network and Geographical Information System

2022 ◽  
Author(s):  
Leila Sherafati ◽  
Hossein Aghamohammadi Zanjirabad ◽  
Saeed Behzadi
Keyword(s):  
Neural Network ◽  
Information System ◽  
Geographical Information System ◽  
Meteorological Parameters ◽  
Interpolation Method ◽  
Temporal Analysis ◽  
Geographical Information ◽  
Temporal Modeling ◽  
Spatiotemporal Model ◽  
Ozone Distribution

Background: Air pollution is one of the most important causes of respiratory diseases that people face in big cities today. Suspended particulates, carbon monoxide, sulfur dioxide, ozone, and nitrogen dioxide are the five major pollutants of air that pose many problems to human health. We aimed to provide an approach for modeling and analyzing the spatiotemporal model of ozone distribution based on Geographical Information System (GIS). Methods: In the first step, by considering the accuracy of different interpolation methods, the Inverse distance weighted (IDW) method was selected as the best interpolation method for mapping the concentration of ozone in Tehran, Iran. In the next step, according to the daily data of Ozone pollutants, the daily, monthly, and annual mean concentrations maps were prepared for the years 2015, 2016, and 2017. Results: Spatial and temporal analysis of the distribution of ozone pollutants in Tehran was performed. The highest concentrations of O3 are found in the southwest and parts of the central part of the city. Finally, a neural network was developed to predict the amount of ozone pollutants according to meteorological parameters. Conclusion: The results show that meteorological parameters such as temperature, velocity and direction of the wind, and precipitation are influential on O3 concentration.

scholarly journals Application of Artificial Neural Network and Geographical Information System Models to Predict and Evaluate the Quality of Diyala River Water, Iraq

2019 ◽  
Vol 26 (1) ◽  
pp. 160-169
Author(s):  
Nawar Omran Al-Musawi ◽  
Fatima Muqdad Al-Rubaie
Keyword(s):  
Neural Network ◽  
Water Quality ◽  
Artificial Neural Network ◽  
Information System ◽  
Geographical Information System ◽  
Geographical Information ◽  
Total Alkalinity ◽  
Artificial Neural ◽  
Diyala River

This research discusses application Artificial Neural Network (ANN) and Geographical Information System (GIS) models on water quality of Diyala River using Water Quality Index (WQI). Fourteen water parameters were used for estimating WQI: pH, Temperature, Dissolved Oxygen, Orthophosphate, Nitrate, Calcium, Magnesium, Total Hardness, Sodium, Sulphate, Chloride, Total Dissolved Solids, Electrical Conductivity and Total Alkalinity. These parameters were provided from the Water Resources Ministryfrom seven stations along the river for the period 2011 to 2016. The results of WQI analysis revealed that Diyala River is good to poor at the north of Diyala province while it is poor to very polluted at the south of Baghdad City. The selected parameters were subjected to Kruskal-Wallis test for detecting factors contributing to the degradation of water quality and for eliminating independent variables that exhibit the highest contribution in p-value. The analysis of results revealed that ANN model was good in predicting the WQI. The confusion matrix for Artificial Neural Model (NNM) gave almost 96% for training, 85.7% for testing and 100% for holdout. In relation to GIS, six color maps of the river have been constructed to give clear images of the water quality along the river.

Sign in / Sign up

Export Citation Format

Share Document