Prediction Mapping Using GIS Data and Advanced ML Algorithms

eXtreme Gradient Boosting, K Nearest Neighbour, Naïve Bayes, Random Forest for Prediction Geo-Hazards and Air pollution

4.55 (113 reviews)
Udemy
platform
English
language
Engineering
category
822
students
16 hours
content
Sep 2023
last update
$44.99
regular price

What you will learn

Two applications of susceptibility prediction mapping in GIS, 1) Landslides prediction maps 2) Ambient air pollution prediction maps

Step by step analysis of ML algorithms for classification: eXtreme Gradient Boosting (XGBoost) K nearest neighbour (KNN) Naïve Bayes (NB) Random forest (RF)

Run classification based algorithms with training data model accuracy, Kappa index, variables importance, sensitivity analysis of explanatory and response data

Hyper-parameter optimization procedure and application

Model accuracy test and validation using; confusion matrix and results validation using AUC value under ROC plot

Produce prediction maps using Raster and vector dataset

Description

In this course, four machine learning supervised classification based techniques used with remote sensing and geospatial resources data to predict two different types of applications:

     Project 1: Data of Multi-labeled target prediction via multi-label classification (multi class problem). Target (Y) that has 3 labeled classes (instead of Numbers): Names, description, ordinal value (small, large, X-large)..Multiple output maps. Like:

  • Increase specific type of species in certain areas and its relationship with surrounding conditions.

  • Air pollution limits prediction (Good, moderate, unhealthy, Hazardous..)

  • Complex diseases types: potential risk factors and their effects on the disease are investigated to identify risk factors that can be used to develop prevention or intervention strategies.

  • Course application:  Prediction of concentration of particulate matter of less than 10 µm diameter (PM10)

  • This project was published as research articles using similar materials and with major part of analysis (with slight modification to the code). "Demystifying uncertainty in PM10 susceptibility mapping using variable drop-off in extreme-gradient boosting (XGB) and random forest (RF) algorithms" in Environmental Science and Pollution Research journal.



    Project 2: Data of Binary labeled target prediction. Target with 2 classes: Yes and No, Slides and No slide, Happened –Not happened, Contaminated- Clean.

  • Flooded areas and it contribution factors like topographic and climate data.

  • Climate change related consequences and its dragging factors like urban heat islands and it relationship with land uses.

  • Oil spills: polluted and non polluted.

  • Course application: Landslide susceptibility mapping in prone area.

  • If you are previously enrolled in my previous course using ANN, then you have the chance to compare the outcomes, as we used the same landslide data here.

Eventually, all the measured data (training and testing), were used to produce the prediction map to be used in further GIS analysis or directly to be presented to decision makers or writing research article in SCI journals.

This course considered the most advanced, in terms of analysis models and output maps that successfully invested in the (1) machine learning algorithm and geospatial domains; (2) free available data of remote sensing in data scarce environment.


IMPORTANT:

LaGriSU Version 2023_03_09 is available (Free) to download using Github link

(search for /Althuwaynee/LaGriSU_Landslide-Grid-and-Slope-Units-QGIS_ToolPack)



*LaGriSU (automatic extraction of training / testing thematic data using Grid and Slope units)


Best regards

Omar AlThuwaynee


Content

Introduction and Course Content : Get to know what will we talk about!

Course contents
Course applications: Landslide and Air pollution prediction analysis
Projects data, study areas and applications extent
Expected outcomes: What will we achieve together!

Practical summary about the classification based machine learning algorithms!

CARET package in R
Hyperparameters optimization (model tuning) in machine learning
eXtreeme Gradient Boosting (XGBoost) classifier machine learning
K- nearest neighbors (KNN) classifier machine learning
Naive Bayes (NB) classifier machine learning
Ensemble Random forest (RF) classifier machine learning
Selection of training and testing data concept
Current computer and software's specifications that used in the course

Project 1: PM10 prediction mapping : Data record pre-processing and data entry

PM10 readings pre-processing and input data preparation in Excel
Allocate the air monitoring stations and record data entry in QGIS
PM10 readings conversion to WHO limits in QGIS

Project 1 PM10 prediction mapping : Input data-frame processing and production

Preparation of PM10 prediction remote sensing variables data-list
Landsat 8 imagery download
Visualization of downloaded Landsat 8 images
Processing of Landsat 8 bands and indices in R
Processing of Land Surface Temperature (LST) in R
Processing of average monthly and annual Landsat 8 bands and indices in R
Processing and production of road networks variable in QGIS
Preparation of input dataframe (target and conditioning factors) in QGIS
Finalize input variables and convert it to CSV format file in QGIS for modeling

Project 1 PM10 prediction mapping : modeling of advanced ML classifiers in R

XGBoost algorithm: Data entry and visualization in R
XGBoost algorithm: Run of train default function
XGBoost algorithm: Hyper-parameter optimization and plot (model tuning)
XGBoost algorithm: AUC value of ROC plot
XGBoost algorithm: Fit optimized model using all inventory observations
XGBoost algorithm: Conversion to dataframe and scaling of Raster images
XGBoost algorithm: Probability prediction maps production
XGBoost algorithm: Classification prediction maps production
NB algorithm: ggplot of linearity between target and independents and variables
NB algorithm: Run of train default function
NB algorithm: Hyper-parameter optimization, AUC of ROC plot & normalized Rasters
NB algorithm: Probability and classification prediction maps production
KNN algorithm: Run of train function and hyper-parameter optimized models
KNN algorithm: AUC of ROC and probability and classification prediction maps
RF algorithm: Data entry and train function using Grid search tuning
RF algorithm: train function using Random search tuning and AUC of ROC
RF algorithm: Scaling and conversion of raster images to dataframe
RF algorithm: Probability prediction map
RF algorithm: Classification prediction map
Summary and Visualization of 4 algorithms prediction resultant maps in QGIS

Project 2 Landslide : Create training and testing data in QGIS

Adding my developed tools to QGIS processing library
Create Land Cover map (convert string observations to numeric) in QGIS
Run the tools Step 1
Run the tools Step 2
Run the tools Step 3

Project 2 Landslide prediction mapping : pre-processing training data in Excel

Excel work step 1
Excel work step 2

Project 2 Landslide prediction mapping : modeling of advanced ML classifiers

XGBoost algorithm : Training and testing data entry in R
XGBoost algorithm : Run train function using default settings
XGBoost algorithm: Hyper-parameter optimization (model tuning) and pairs plot
XGBoost algorithm: AUC of ROC plot and important technical error
XGBoost algorithm: Run optimized model and probability prediction maps
XGBoost algorithm: Classification prediction map production
KNN algorithm : Data entry and visualization of target and other variables
KNN algorithm: Run of train function and hyper-parameter optimized models
KNN algorithm: AUC of ROC plot and technical issues with data entry
KNN algorithm: probability prediction maps
KNN algorithm: classification prediction map
NB algorithm: Training data entry and visualization of variables
NB algorithm: Train function and Hyper-parameters and AUC of ROC plot
NB algorithm: Probability and classification prediction maps production
RF algorithm: Data entry of training data variables
RF algorithm: default train function and Hyper-parameter and AUC of ROC plot
RF algorithm: Probability and classification prediction maps
Summary and Visualization of 4 algorithms prediction maps in QGIS

Projects Conclusion and main remarks of the presented course

Summary: Let us sum up everything and recap what we discussed earlier!

Screenshots

Prediction Mapping Using GIS Data and Advanced ML Algorithms - Screenshot_01Prediction Mapping Using GIS Data and Advanced ML Algorithms - Screenshot_02Prediction Mapping Using GIS Data and Advanced ML Algorithms - Screenshot_03Prediction Mapping Using GIS Data and Advanced ML Algorithms - Screenshot_04

Reviews

Malakai
June 6, 2023
Wow just wow thank you so much for the great insights Dr. Omar AlThuwaynee helps me a lot in my research thesis
Paulo
October 3, 2020
I highly recommend this content to all those who are interested in machine learning for landslide forecasting mapping. Dr. Omar Althuwaynee has made an approach that covers you from the beginning to the end of the map, even if you are new to the R software. Furthermore, this course helped me a lot in my research and it made me interested in R programming.
Naser
August 25, 2020
Dear Dr. Omar F. AlThuwaynee. You are such a great teacher. I have learned a lot from your courses and also applied in my research. Please keep doing the good work. We look forward to get more relevant courses from you. What about Deep Learning Neural Network? ;-)
Ujjwal
August 3, 2020
Very nicely explained the content with practical example. This has helped to understand the basic concept with ease.
Mohammad
July 29, 2020
the course is good and informative. However there is some problem in understanding what the teacher is saying due to his accent and since the captions are automatic they are wrong. Please provide correct captions

Charts

Price

Prediction Mapping Using GIS Data and Advanced ML Algorithms - Price chart

Rating

Prediction Mapping Using GIS Data and Advanced ML Algorithms - Ratings chart

Enrollment distribution

Prediction Mapping Using GIS Data and Advanced ML Algorithms - Distribution chart
2733334
udemy ID
1/2/2020
course created date
3/22/2020
course indexed date
Bot
course submited by