Prediction Mapping Using GIS Data and Advanced ML Algorithms
 Description
 Curriculum
 FAQ
 Reviews
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 Multilabeled target prediction via multilabel classification (multi class problem). Target (Y) that has 3 labeled classes (instead of Numbers): Names, description, ordinal value (small, large, Xlarge)..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 Āµm diameter (PM10)
Project 2: Data of Binary labeled target prediction. Target with 2 classes: Yes and No, Slides and No slide, Happened āNot 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.

5CARET package in R

6Hyperparameters optimization (model tuning) in machine learning

7eXtreeme Gradient Boosting (XGBoost) classifier machine learning

8K nearest neighbors (KNN) classifier machine learning

9Naive Bayes (NB) classifier machine learning

10Ensemble Random forest (RF) classifier machine learning

11Selection of training and testing data concept

12Current computer and software's specifications that used in the course

16Preparation of PM10 prediction remote sensing variables datalist

17Landsat 8 imagery download

18Visualization of downloaded Landsat 8 images

19Processing of Landsat 8 bands and indices in R

20Processing of Land Surface Temperature (LST) in R

21Processing of average monthly and annual Landsat 8 bands and indices in R

22Processing and production of road networks variable in QGIS

23Preparation of input dataframe (target and conditioning factors) in QGIS

24Finalize input variables and convert it to CSV format file in QGIS for modeling

25XGBoost algorithm: Data entry and visualization in R

26XGBoost algorithm: Run of train default function

27XGBoost algorithm: Hyperparameter optimization and plot (model tuning)

28XGBoost algorithm: AUC value of ROC plot

29XGBoost algorithm: Fit optimized model using all inventory observations

30XGBoost algorithm: Conversion to dataframe and scaling of Raster images

31XGBoost algorithm: Probability prediction maps production

32XGBoost algorithm: Classification prediction maps production

33NB algorithm: ggplot of linearity between target and independents and variables

34NB algorithm: Run of train default function

35NB algorithm: Hyperparameter optimization, AUC of ROC plot & normalized Rasters

36NB algorithm: Probability and classification prediction maps production

37KNN algorithm: Run of train function and hyperparameter optimized models

38KNN algorithm: AUC of ROC and probability and classification prediction maps

39RF algorithm: Data entry and train function using Grid search tuning

40RF algorithm: train function using Random search tuning and AUC of ROC

41RF algorithm: Scaling and conversion of raster images to dataframe

42RF algorithm: Probability prediction map

43RF algorithm: Classification prediction map

44Summary and Visualization of 4 algorithms prediction resultant maps in QGIS

52XGBoost algorithm : Training and testing data entry in R

53XGBoost algorithm : Run train function using default settings

54XGBoost algorithm: Hyperparameter optimization (model tuning) and pairs plot

55XGBoost algorithm: AUC of ROC plot and important technical error

56XGBoost algorithm: Run optimized model and probability prediction maps

57XGBoost algorithm: Classification prediction map production

58KNN algorithm : Data entry and visualization of target and other variables

59KNN algorithm: Run of train function and hyperparameter optimized models

60KNN algorithm: AUC of ROC plot and technical issues with data entry

61KNN algorithm: probability prediction maps

62KNN algorithm: classification prediction map

63NB algorithm: Training data entry and visualization of variables

64NB algorithm: Train function and Hyperparameters and AUC of ROC plot

65NB algorithm: Probability and classification prediction maps production

66RF algorithm: Data entry of training data variables

67RF algorithm: default train function and Hyperparameter and AUC of ROC plot

68RF algorithm: Probability and classification prediction maps

69Summary and Visualization of 4 algorithms prediction maps in QGIS
Social Network