Well Logging Based Lithology Identification Model Establishment Under Data Drift: A Transfer Learning Method
نویسندگان
چکیده
منابع مشابه
Neural Networks Based Lithology Identification
In this paper, a novel neural networks based lithology identification approach is proposed. First, the logging curves are squared so that the noise is filtered off. Second, consecutive segments representing similar stratums are merged so that the dimension of inputs is reduced. Third, data sampling from different logging curves are respectively normalized so that the curves of small magnitude a...
متن کاملLearning Under Persistent Drift
In this paper we study learning algorithms for environments which are changing over time. Unlike most previous work, we are interested in the case where the changes might be rapid but their \direction" is relatively constant. We model this type of change by assuming that the target distribution is changing continuously at a constant rate from one extreme distribution to another. We show in this...
متن کاملA programming method to estimate proximate parameters of coal beds from well-logging data using a sequential solving of linear equation systems
This paper presents an innovative solution for estimating the proximate parameters of coal beds from the well-logs. To implement the solution, the C# programming language was used. The data from four exploratory boreholes was used in a case study to express the method and determine its accuracy. Then two boreholes were selected as the reference, namely the boreholes with available well-logging ...
متن کاملActive Transfer Learning under Model Shift
Transfer learning algorithms are used when one has sufficient training data for one supervised learning task (the source task) but only very limited training data for a second task (the target task) that is similar but not identical to the first. These algorithms use varying assumptions about the similarity between the tasks to carry information from the source to the target task. Common assump...
متن کاملA Meta-learning Method for Concept Drift
The knowledge hidden in evolving data may change with time, this issue is known as concept drift. It often causes a learning system to decrease its prediction accuracy. Most existing techniques apply ensemble methods to improve learning performance on concept drift. In this paper, we propose a novel meta learning approach for this issue and develop a method: Multi-Step Learning (MSL). In our me...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Sensors
سال: 2020
ISSN: 1424-8220
DOI: 10.3390/s20133643