Since frequent severe droughts are lengthening the dry season in the Amazon Rainforest, it is important to detect wildfires promptly and forecast possible spread for effective suppression response. Current wildfire detection models are not versatile enough for the low-technology conditions of South American hot spots. This deep learning study first trains a Fully Convolutional Neural Network on Landsat 8 images of Ecuador and the Galapagos, using Green and Short-wave Infrared bands to predict pixel-level binary fire masks. This model achieves a 0.962 validation F2 score and a 0.932 F2 score on test data from Guyana and Suriname. Afterward, image segmentation is conducted on the Cirrus band using K-Means Clustering to simplify continuous pixel values into three discrete classes representing differing degrees of cirrus cloud contamination. Three additional Convolutional Neural Networks are trained to conduct a sensitivity analysis measuring the effect of simplified features on model accuracy and train time. The Experimental model trained on the segmented cirrus images provides a statistically significant decrease in train time compared to the Control model trained on raw cirrus images, without compromising binary accuracy. This proof of concept reveals that feature engineering can improve the performance of wildfire detection models by lowering computational expense.

The rapid urban growth and development have been putting increasing pressure on the environment including urban parks and green spaces. The green spaces are essential to improve the urban areas and to provide quality life to the urban population. Green spaces generally include lawns, public parks, gardens, street landscapes, forests, etc. In this regard, technologies such as satellite imagery and AI/ML can support the urban developers as well as the land managers to monitor and support decision-making for sustainable urban development in dense urban environments and prevent flooding conditions in urban areas by gathering high-resolution details of the urban area(s). Further, satellite images can provide detailed analysis for detecting major changes in the urban land cover and land use that allows frequent coverage and overlaying of different time sequences to classify environmentally safe and sustainable areas for any proposed development area(s).

Module #6 of Metis' Data Science and Machine Learning bootcamp is all wrapped up! For this module we focused on Deep Learning, working with non-tabular data, and building models using Google's Tensorflow library. For our project, we were tasked with creating an image classification model to solve for a real-world problem. This module took place during the Russian invasion of Ukraine. The conflict has highlighted the use of satellite imagery by journalists, human rights organizations, and open-source intelligence analysts.

Crop maps are crucial for agricultural monitoring and food management and can additionally support domain-specific applications, such as setting cold supply chain infrastructure in developing countries. Machine learning (ML) models, combined with freely-available satellite imagery, can be used to produce cost-effective and high spatial-resolution crop maps. However, accessing ground truth data for supervised learning is especially challenging in developing countries due to factors such as smallholding and fragmented geography, which often results in a lack of crop type maps or even reliable cropland maps. Our area of interest for this study lies in Himachal Pradesh, India, where we aim at producing an open-access binary cropland map at 10-meter resolution for the Kullu, Shimla, and Mandi districts. To this end, we developed an ML pipeline that relies on Sentinel-2 satellite images time series. We investigated two pixel-based supervised classifiers, support vector machines (SVM) and random forest (RF), which are used to classify per-pixel time series for binary cropland mapping. The ground truth data used for training, validation and testing was manually annotated from a combination of field survey reference points and visual interpretation of very high resolution (VHR) imagery. We trained and validated the models via spatial cross-validation to account for local spatial autocorrelation and selected the RF model due to overall robustness and lower computational cost. We tested the generalization capability of the chosen model at the pixel level by computing the accuracy, recall, precision, and F1-score on hold-out test sets of each district, achieving an average accuracy for the RF (our best model) of 87%. We used this model to generate a cropland map for three districts of Himachal Pradesh, spanning 14,600 km2, which improves the resolution and quality of existing public maps.

Geospatial Data Analyses & Remote Sensing: 5 Classes in 1 Do you need to design a GIS map or satellite-imagery based map for your Remote Sensing or GIS project but you don't know how to do this? Have you heard about Remote Sensing object-based image analysis and machine learning or maybe QGIS or Google Earth Engine but did not know where to start with such analyses? Do you find Remote Sensing and GIS manuals too not practical and looking for a course that takes you by hand, teach you all the concepts, and get you started on a real-life GIS mapping project? I'm very excited that you found my Practical Geospatial Masterclass on Geospatial Data Analyses & Remote Sensing. This course provides and information that is usually delivered in 4 separate Geospatial Data Analyses & Remote Sensing courses, and thus you with learning all the necessary information to start and advance with Geospatial analysis and includes more than 9 hours of video content, plenty of practical analysis, and downloadable materials.

Become proficient in satellite remote sensing, spatial analysis principles, methods, applications, sensors, and GIS! Get this course for only 9.99. Do you find that other remote sensing courses are too short and vague, and do not prepare you for real world problems? Are you looking for a course that goes IN-DEPTH and teaches you all the fundamentals of remote sensing? My course provides a solid foundation to carry out practical, real life remote sensing spatial data analysis and gives you the techniques and knowledge to tackle a variety of geological and environmental problems. This course provides an introduction to remote sensing - the acquisition of information about the earth from a distance, typically via airborne and spaceborne sensors.

Learn to apply machine learning, remote sensing, big spatial data using the Google Earth Engine cloud computing. Do you want to learn how to access, process and analyze remote sensing data using open source cloud-based platforms? Do you want to master machine learning algorithms to predict Earth Observation big data? Do you want to start a spatial data scientist career in the geospatial industry? Enroll in my new course to master Machine Learning with Remote Sensing in Google Earth Engine.

Extracting cultivated land accurately from high-resolution remote images is a basic task for precision agriculture. This report introduces our solution to the iFLYTEK challenge 2021 cultivated land extraction from high-resolution remote sensing image. The challenge requires segmenting cultivated land objects in very high-resolution multispectral remote sensing images. We established a highly effective and efficient pipeline to solve this problem. We first divided the original images into small tiles and separately performed instance segmentation on each tile. We explored several instance segmentation algorithms that work well on natural images and developed a set of effective methods that are applicable to remote sensing images. Then we merged the prediction results of all small tiles into seamless, continuous segmentation results through our proposed overlap-tile fusion strategy. We achieved the first place among 486 teams in the challenge.

Data science covers the full spectrum of deriving insight from data, from initial data gathering and interpretation, via processing and engineering of data, and exploration and modeling, to eventually producing novel insights and decision support systems. Data science can be viewed as overlapping or broader in scope than other data-analytic methodological disciplines, such as statistics, machine learning, databases, or visualization.10 To illustrate the breadth of data science, consider, for example, the problem of recommending items (movies, books, or other products) to customers. While the core of these applications can consist of algorithmic techniques such as matrix factorization, a deployed system will involve a much wider range of technological and human considerations. These range from scalable back-end transaction systems that retrieve customer and product data in real time, experimental design for evaluating system changes, causal analysis for understanding the effect of interventions, to the human factors and psychology that underlie how customers react to visual information displays and make decisions. As another example, in areas such as astronomy, particle physics, and climate science, there is a rich tradition of building computational pipelines to support data-driven discovery and hypothesis testing. For instance, geoscientists use monthly global landcover maps based on satellite imagery at sub-kilometer resolutions to better understand how the Earth's surface is changing over time.50 These maps are interactive and browsable, and they are the result of a complex data-processing pipeline, in which terabytes to petabytes of raw sensor and image data are transformed into databases of a6utomatically detected and annotated objects and information. This type of pipeline involves many steps, in which human decisions and insight are critical, such as instrument calibration, removal of outliers, and classification of pixels. The breadth and complexity of these and many other data science scenarios means the modern data scientist requires broad knowledge and experience across a multitude of topics. Together with an increasing demand for data analysis skills, this has led to a shortage of trained data scientists with appropriate background and experience, and significant market competition for limited expertise. Considering this bottleneck, it is not surprising there is increasing interest in automating parts, if not all, of the data science process.

The earth observation industry provides satellite imagery with high spatial resolution and short revisit time. To allow efficient operational employment of these images, automating certain tasks has become necessary. In the defense domain, aircraft detection on satellite imagery is a valuable tool for analysts. Obtaining high performance detectors on such a task can only be achieved by leveraging deep learning and thus us-ing a large amount of labeled data. To obtain labels of a high enough quality, the knowledge of military experts is needed.We propose a hybrid clustering active learning method to select the most relevant data to label, thus limiting the amount of data required and further improving the performances. It combines diversity- and uncertainty-based active learning selection methods. For aircraft detection by segmentation, we show that this method can provide better or competitive results compared to other active learning methods.