วีดีโอ

Hi Dr Azad, did you manually select known areas of wheat and barley for the test data ?

Hi Dr. Azad Rasul, thank you very much for the great tutorial! For Model 2 which has one more layer than Model 1, I wonder why its accuracy is lower than Model 1?

www.udemy.com/course/programming-for-scientific-research/?referralCode=6B1CDFAB54BF528832BF

www.udemy.com/course/ai-for-geospatial-analysis/?referralCode=756925DC2106C34C6DBE

❤❤❤❤❤دەستت خۆشبێت کاک دکتۆر، کاک دکتۆر هەتا چەند Ai جێگای متمانەیە؟

www.udemy.com/course/python-for-researchers/?referralCode=886CCF5C552567F1C4E7

www.udemy.com/course/r-for-research/?referralCode=B6DCFDE343F0592EA61A

www.udemy.com/course/ai-for-geospatial-analysis/?referralCode=756925DC2106C34C6DBE

❤❤❤❤❤❤❤ دەستت خۆشبێت کاک دکتۆر گوڵ

The link to the code on my GitHub repository is: github.com/Azad77/Detecting-and-Counting-Plants-Using-Computer-Vision-Techniques

دەستت خۆشبێت کاک دکتۆر❤❤❤❤❤❤

❤❤❤❤❤❤دەستت خۆشبێت کاک دکتۆر

The link to the code on my GitHub Repo: github.com/Azad77/Modeling-and-Predicting-Crop-Health-Using-RS-Data-and-Neural-Networks/tree/main

Wonderful Dr. Azad keep it going.🙏

A link to the code is: github.com/Azad77/crop-data-analysis/blob/main/Crop%20Data%20Analysis.ipynb

Thank you!

Dastt xosh dktor

The code and data for this tutorial are available in my GitHub repository at: github.com/Azad77/ML_Geospatial_Analysis.

The code and data for this tutorial are available in my GitHub repository at: github.com/Azad77/ML_Geospatial_Analysis.

The code and data for this tutorial are available in my GitHub repository at: github.com/Azad77/ML_Geospatial_Analysis.

The code and data for this tutorial are available in my GitHub repository at: github.com/Azad77/ML_Geospatial_Analysis.

The code and data for this tutorial are available in my GitHub repository at: github.com/Azad77/ML_Geospatial_Analysis.

❤دەستت خۆشبێت کاک دکتۆر❤❤❤

❤❤❤❤❤❤❤دەستت خۆشبێت کاک دکتۆر

❤❤❤❤❤❤❤ دەستخۆشبێت کاک دکتۆری گوڵ

Code Repository: github.com/Azad77/LULC_CNN_EuroSAT/blob/main/CNNs_LULC_Classification_EuroSAT_Azad_Rasul.ipynb

دەستتخۆشبێت کاک دکتۆری گوڵ

❤❤❤❤❤❤❤❤❤❤❤❤❤❤❤❤❤❤

❤❤❤❤❤❤❤❤ دەستت خۆشبێت کاک دکتۆری گوڵ

❤❤❤❤❤❤❤❤دەستت خۆشبێت کاک دکتۆر بەڕێز و گوڵ

www.udemy.com/course/ai-for-geospatial-analysis/?referralCode=756925DC2106C34C6DBE

www.udemy.com/course/ai-for-geospatial-analysis/?referralCode=756925DC2106C34C6DBE

I loved all the videos here dear

Great Video! ❤

This is the valuable information, thank you so much Dr. Azad 🙏

Wonderful 👍

Great Dr. Azad 🙏

Thank you so much Dr. Azad for this valuable information, big respect 🙏

smartrs.uk/comparison-of-different-ml-classifiers-on-synthetic-dataset

# Importing necessary libraries import matplotlib.pyplot as plt # Library for plotting import numpy as np # Library for numerical operations from sklearn.ensemble import RandomForestClassifier from matplotlib.colors import ListedColormap # For customizing colormap from sklearn.datasets import make_classification # For generating synthetic datasets from sklearn.inspection import DecisionBoundaryDisplay # For displaying decision boundaries from sklearn.model_selection import train_test_split # For splitting dataset into train and test sets from sklearn.neighbors import KNeighborsClassifier # k-Nearest Neighbors classifier from sklearn.neural_network import MLPClassifier # Multi-layer Perceptron classifier from sklearn.pipeline import make_pipeline # For creating a pipeline of transformers and estimators from sklearn.preprocessing import StandardScaler # For standardizing features from sklearn.tree import DecisionTreeClassifier # Decision Tree classifier # List of classifier names names = [ "Nearest Neighbors", "Decision Tree", "Random Forest", "Neural Net" ] # List of classifiers classifiers = [ KNeighborsClassifier(3), # k-Nearest Neighbors with k=3 DecisionTreeClassifier(max_depth=5, random_state=42), # Decision Tree Classifier with max depth of 5 RandomForestClassifier(max_depth=5, n_estimators=10, max_features=1, random_state=42), # Random Forest Classifier MLPClassifier(alpha=1, max_iter=1000, random_state=42) # Multi-layer Perceptron Classifier ] # Generating a complex synthetic dataset X, y = make_classification( n_samples=1000, # Number of samples in the dataset n_features=20, # Number of features in the dataset n_redundant=2, # Number of redundant features n_informative=10, # Number of informative features n_clusters_per_class=2, # Number of clusters per class random_state=1 # Random seed for reproducibility ) rng = np.random.RandomState(2) X += 2 * rng.uniform(size=X.shape) # Adding noise to the dataset # Using only the first two features for visualization X = X[:, :2] # Splitting the dataset into training and testing sets X_train, X_test, y_train, y_test = train_test_split( X, y, test_size=0.4, random_state=42 ) # Creating a figure for plotting figure = plt.figure(figsize=(18, 6)) x_min, x_max = X[:, 0].min() - 0.5, X[:, 0].max() + 0.5 y_min, y_max = X[:, 1].min() - 0.5, X[:, 1].max() + 0.5 # Plotting the dataset cm = plt.cm.RdBu cm_bright = ListedColormap(["#FF0000", "#0000FF"]) ax = plt.subplot(1, len(classifiers) + 1, 1) ax.set_title("Input data") ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright, edgecolors="k") ax.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright, alpha=0.6, edgecolors="k") ax.set_xlim(x_min, x_max) ax.set_ylim(y_min, y_max) ax.set_xticks(()) ax.set_yticks(()) # Iterate over classifiers for i, (name, clf) in enumerate(zip(names, classifiers), start=2): ax = plt.subplot(1, len(classifiers) + 1, i) # Constructing a pipeline with standard scaler and the classifier clf = make_pipeline(StandardScaler(), clf) # Fitting the classifier clf.fit(X_train, y_train) # Calculating the accuracy score score = clf.score(X_test, y_test) # Plotting decision boundaries DecisionBoundaryDisplay.from_estimator( clf, X, cmap=cm, alpha=0.8, ax=ax, eps=0.5 ) # Plotting training and testing points ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright, edgecolors="k") ax.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright, edgecolors="k", alpha=0.6) ax.set_xlim(x_min, x_max) ax.set_ylim(y_min, y_max) ax.set_xticks(()) ax.set_yticks(()) ax.set_title(name) # Adding accuracy score as text on each subplot ax.text(x_max - 0.3, y_min + 0.3, ("%.2f" % score).lstrip("0"), size=15, horizontalalignment="right") # Adjusting layout and displaying the plot plt.tight_layout() plt.show()

سووپاسی ماندووبوونەکانتم کاک دکتۆر دەستت خۆشبێت ❤❤

Here is the link to the code on my blog: smartrs.uk/calculating-common-remote-sensing-indices-in-python.

❤❤❤

دەستت خۆشبێت کاک دکتۆری گوڵ خودا خێرت بنووسێت

# !pip install pylst # Import the calculate_zs function from the zonstat module in the pylst.spatial_analysis package from pylst.spatial_analysis.zonstat import calculate_zs # Define the path to the shapefile containing the administrative boundaries (in this case, Erbil_Admi_3.shp) shapefile_path = "D:\\GeoAI_Master_2024\\GeoAI_Master_2024_Lecture2_Geospatial_Data_in_Python\data\\Erbil_Shapefile\\Erbil_Admi_3.shp" # Define the path to the raster file (in this case, Chirps_Erbil.tif) for spatial analysis raster_path = "D:\\GeoAI_Master_2024\\GeoAI_Master_2024_Lecture2_Geospatial_Data_in_Python\data\\Chirps_Erbil.tif" # Call the calculate_zs function, passing the shapefile and raster paths as arguments # This function performs zone-based statistics, calculating values for each zone in the shapefile from the corresponding raster data df = calculate_zs(shapefile_path, raster_path) # Print the resulting DataFrame that contains the calculated zone-based statistics print(df) # Save Result of df.to_csv("zonal_stats_chirps.csv", index=True)

❤❤❤❤❤❤❤

دەستت خۆشبێت کاک دکتۆری گوڵ

❤❤دەستت خۆشبێت کاک دکتۆر

Here is the link to the code on my blog:smartrs.hashnode.dev/enhance-the-accuracy-of-crop-classification-in-google-earth-engine-using-the-random-forest

hashnode.com/edit/clvqcgh9t000709jnc890azs1