Machine learning in earth sciences

<p>Applications of <a href="/facts/Machine_learning/e0w0XJTu">machine learning</a> (ML) in <a href="/facts/Earth_sciences/rQsXCSbM">earth sciences</a> include <a href="/facts/Geological_mapping/HhK3dQ87">geological mapping</a>, <a href="/facts/Leak_detection/rq2ujfIX">gas leakage detection</a> and <a href="/facts/Geology/WGvVRIYF">geological</a> <a href="/facts/Feature_(computer_vision)/GdfWRp5U">feature identification</a>. Machine learning is a subdiscipline of <a href="/facts/Artificial_intelligence/lJGauQwX">artificial intelligence</a> aimed at developing programs that are able to classify, cluster, identify, and analyze vast and complex <a href="/facts/Data_set/eDvegUTK">data sets</a> without the need for explicit programming to do so. <a href="/facts/Earth_science/rQsXCSbM">Earth science</a> is the study of the origin, evolution, and future of the <a href="/facts/Earth/HLLmDfj0">Earth</a>. The earth's system can be subdivided into four major components including the <a href="/facts/Lithosphere/1mqaxASd">solid earth</a>, <a href="/facts/Atmosphere/oUpLaGRF">atmosphere</a>, <a href="/facts/Hydrosphere/RbJmcSX6">hydrosphere</a>, and <a href="/facts/Biosphere/P1ltA4sb">biosphere</a>.
</p><p>A variety of algorithms may be applied depending on the nature of the task. Some algorithms may perform significantly better than others for particular objectives. For example, <a href="/facts/Convolutional_neural_network/kHEdnmGU">convolutional neural networks</a> (CNNs) are good at interpreting images, whilst more general <a href="/facts/Neural_network_(machine_learning)/6V1jMlkx">neural networks</a> may be used for <a href="/facts/Soil_classification/gru7kDvL">soil classification</a>, but can be more computationally expensive to train than alternatives such as <a href="/facts/Support_vector_machine/XobxpdBG">support vector machines</a>. The range of tasks to which ML (including <a href="/facts/Deep_learning/JLuwD3ea">deep learning</a>) is applied has been ever-growing in recent decades, as has the development of other technologies such as <a href="/facts/Unmanned_aerial_vehicle/qt87T19t">unmanned aerial vehicles</a> (UAVs), ultra-high resolution <a href="/facts/Remote_sensing_(geology)/U96sKxe5">remote sensing</a> technology, and <a href="/facts/High-performance_computing/HT9NwGAN">high-performance computing</a>. This has led to the availability of large high-quality datasets and more advanced algorithms.
</p>

Machine learning in earth sciences open-in-new

Machine learning in earth sciences