• Corpus ID: 52158025

Identifying Land Patterns from Satellite Imagery in Amazon Rainforest using Deep Learning

  title={Identifying Land Patterns from Satellite Imagery in Amazon Rainforest using Deep Learning},
  author={Somnath Rakshit and Soumyadeep Debnath and Dhiman Mondal},
The Amazon rainforests have been suffering widespread damage, both via natural and artificial means. Every minute, it is estimated that the world loses forest cover the size of 48 football fields. Deforestation in the Amazon rainforest has led to drastically reduced biodiversity, loss of habitat, climate change, and other biological losses. In this respect, it has become essential to track how the nature of these forests change over time. Image classification using deep learning can help speed… 

Figures and Tables from this paper

Change Detection of Deforestation in the Brazilian Amazon Using Landsat Data and Convolutional Neural Networks

This study attempted to map the deforestation between images approximately one year apart, specifically between 2017 and 2018 and between 2018 and 2019, and found that the DL models were better in most performance metrics including the Kappa index, F1 score, and mean intersection over union (mIoU) measure.

Monthly Deforestation Prediction using eXtreme Gradient Boosting based on MODIS EVI time series

The Dry Chaco region (DCF) has the highest absolute deforestation rates in Argentina. In this study, we evaluated the performance of the Extreme Gradient Boosting (XGboost) algorithm to detect

Satellite Imagery for Deforestation Prediction using Deep Learning

This work uses advanced machine learning algorithms to detect deforestation in vulnerable places using algorithms like detection and segmentation for identifying the lands which are deforested.

Applications of computer vision to population dynamics: detecting flowering trees in high-resolution cube-sat imagery

The recent advances and widespread availability of highresolution satellite imagery and other remote sensing data have provided new avenues and applications for image analysis techniques. Satellite


An new method for automatic deforestation detection, based on semantic segmentation, is proposed using ResUnet-a multitasking with a new Semi-Supervised Change vector analysis (CVA) task to study the contribution of CVA to the change detection problem and compare its relevance with the other tasks.

Deep learning in gastric tissue diseases: a systematic review

A systematic review of applications of deep learning in gastric tissue disease analysis by digital histology, endoscopy and radiology images highlighted the high potential and shortcomings in deep learning research studies applied to gastric cancer, ulcer, gastritis and non-malignant diseases.

Top-k Influential Nodes Identification Based on Activity Behaviors in Egocentric Online Social Networks

This work proposes a model to identify top-k influential nodes by evaluating Normalized Influence Factors of network members based on their activity behaviors in egocentric OSNs.

Recommending Influenceable Targets based on Influence Propagation through Activity Behaviors in Online Social Media

An effective model has been discussed in egocentric OSN by incorporating an efficient influence measured Recommendation System in order to generate a list of top most influenceable target users among all connected network members for any specific social network user.



DeepRootz: Classifying satellite images of the Amazon rainforest

The Amazon rainforest is a critical, yet highly threatened South American natural resource. The size and density of the forest make monitoring by land or low-air expensive and intractable. Recent

Multi-label Classification of Satellite Images with Deep Learning

A Convolutional Neural Network model is implemented to perform multi-label classification of Amazon satellite images to enable stakeholders to pinpoint where deforestation and associated illegal activity is taking place and craft targeted policy to limit its deleterious effects.

Amazon Rainforest Deforestation Daily Detection Tool Using Artificial Neural Networks and Satellite Images

The main purpose of this work was the development of a tool to detect daily deforestation in the Amazon rainforest, using satellite images from the MODIS/TERRA [1] sensor and Artificial Neural

ImageNet classification with deep convolutional neural networks

A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective.

Visualizing and Understanding Convolutional Networks

A novel visualization technique is introduced that gives insight into the function of intermediate feature layers and the operation of the classifier in large Convolutional Network models, used in a diagnostic role to find model architectures that outperform Krizhevsky et al on the ImageNet classification benchmark.

Very Deep Convolutional Networks for Large-Scale Image Recognition

This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.

OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks

This integrated framework for using Convolutional Networks for classification, localization and detection is the winner of the localization task of the ImageNet Large Scale Visual Recognition Challenge 2013 and obtained very competitive results for the detection and classifications tasks.

Self-taught learning: transfer learning from unlabeled data

An approach to self-taught learning that uses sparse coding to construct higher-level features using the unlabeled data to form a succinct input representation and significantly improve classification performance.

Adam: A Method for Stochastic Optimization

This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.

TensorFlow: A system for large-scale machine learning

The TensorFlow dataflow model is described and the compelling performance that Tensor Flow achieves for several real-world applications is demonstrated.