• A.Vijaya Vahini

Deforestation detection using convolutional neural network is a method to calculate the amount of deforestation occurred by taking input as satellite images of before deforestation and after deforestation. There are four modules in this project. First module is training. In this, we need to train the model using satellite images which are taken from the Prodes database. The features of the images are extracted by using various layers like convolution2dlayer, batch normalization layer, ReLU layer, maxpooling2dlayer. Second module is a classification module where a random satellite image is compared with a trained model from the first module to classify it into forest or deforest area. Next module is the testing module where we will get a confusion matrix to know the accuracy of the classification of images by the trained model. The last module is block division. In this a method will take satellite images of the area before deforestation and after deforestation and give the result as the amount of deforestation occurred in percentage.

Deforestation, CNN, Convolutional layer

"Deforestation Detection using CNN", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.8, Issue 8, page no.b924-b931, August-2021, Available :http://www.jetir.org/papers/JETIR2108244.pdf

"Deforestation Detection using CNN", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.8, Issue 8, page no. ppb924-b931, August-2021, Available at : http://www.jetir.org/papers/JETIR2108244.pdf