The Paradise Well Analysis Dashboard provides an intuitive environment where well logs, petrophysical data, and seismic-derived machine learning results can be analyzed side by side. Geoscientists can easily load their well logs (with formation tops, curves, etc.) and view them in context with the Paradise multi-attribute classifications or other seismic attributes at the borehole location​. This means you can correlate machine learning classification outcomes directly with traditional well logs and cross-sections.

• Bridge the gap between subsurface models and actual well data.
• Visually overlay interpreted seismic facies (g. SOM* clusters) and even fault detection results along the well path, revealing how lithology and structure intersect at each well​.
• Accelerate QC and calibration of machine learning results against known geology.

This integrated approach gives interpreters greater confidence in identifying reservoir intervals and subtle features.

The new Well Log Histograms tool provides a powerful way to analyze well log data statistically and derives insights that inform seismic interpretation. With a few clicks, Paradise will generate histograms showing the distribution of any well log values (such as porosity, clay content, or production indicators) to help interpreters spot trends and outliers. This is extremely useful for quality control and understanding the range of rock properties present in the field. Moreover, the histogram feature doubles as a “hit count” analysis for SOM neurons or ML classes within given depth intervals.

In other words, you can visualize how frequently each machine learning cluster (from a seismic SOM classification) appears in a particular interval of a well or across the entire well.

This capability is invaluable for calibrating the ML results: for example, one can quickly identify which clusters correspond to known productive zones versus non-productive zones by comparing their occurrence in intervals defined as “net reservoir” vs “non-reservoir” based on petrophysical cutoffs. Such statistical correlations between ML neurons and reservoir properties help validate and refine the interpretation – essentially bridging the gap between pattern recognition and physical rock data.

The Well Log Histogram tool thus adds a quantitative lens to the analysis, enabling geoscientists to uncover relationships between seismic-driven classes and actual well log measurements at a glance. This leads to more insightful conclusions about reservoir quality and distribution, grounded in both seismic and well data.

The Machine Learning-based Lithofacies Log Generation in Paradise is a tool for creating new lithofacies logs from your existing well log data. This capability lets geoscientists derive discrete lithology or facies curves using either K-means ML clustering algorithms or rule-based petrophysical cutoffs.

Take a suite of conventional logs (porosity, resistivity, gamma, etc.) and automatically classify the log responses into facies categories. The result is a new log, indexed to depth, that highlights different lithologies or reservoir units as inferred from the data. Alternatively, if you have known cutoff criteria (such as Vclay < X% and Porosity > Y for “net sand”), the tool can apply those rules to generate a facies log.

An interactive analysis dashboard guides you this process, allowing for review of histograms and cluster statistics to understand and refine the defined lithofacies. The generated lithofacies logs can be used directly within Paradise (feeding into the Lithofacies Prediction described here) or exported for use in other interpretation platforms​. By automating lithology log creation, this feature ensures consistency across wells and removes tedious manual classification.

The Well Log Cross Plot tool graphically displays the relationship between log curves and machine learning results, revealing pay intervals on the Well Cross Section depth track. Cross Plots highlight specific neurons in conjunction with log values most associated with production. Apply the Well Cross Plot tool to obtain these results quickly and easily:

• Bring seismic data resolution to borehole log and lithofacies scale in feet/meters via attributes, Machine Learning (ML) Stratigraphic Analysis using Self-Organizing Maps (SOMs), and ML Geobodies
• Extract seismic data along the borehole as attributes, SOM results, or probability results, and easily modify the associated color bars
• Display digital well logs, TD charts, formation tops, and cross-sections in straightforward displays

Apply the companion Well Log Viewer to analyze logs versus machine learning results, and identify which neurons correspond to reservoir petrophysical properties. Examine different ML topologies versus well logs to determine which topology is optimum. Then, convert the classes corresponding to production into ML geobodies.

Learn how geoscientists are using the Paradise® AI Workbench to verify well log data

Applying ML Technologies in the Niobrara Formation to Produce an Integrated Classification Volume Calibrated to Wells

Identify Reservoirs by Combining Machine Learning, Petrophysics, and Bi-variate Statistics

Net Reservoir Discrimination through Multi-Attribute Analysis at Single Sample Scale