CACI International has patented a system to predict total electron content in the ionosphere using machine learning models. The method involves obtaining a dataset, inputting it into a combination of LSTM and GAN neural networks, and observing performance improvement over time. The prediction is made for regions with specific ground transmitter criteria. GlobalData’s report on CACI International gives a 360-degree view of the company including its patenting strategy. Buy the report here.

According to GlobalData’s company profile on CACI International, was a key innovation area identified from patents. CACI International's grant share as of February 2024 was 72%. Grant share is based on the ratio of number of grants to total number of patents.

Predicting total electron content in ionosphere using machine learning

Source: United States Patent and Trademark Office (USPTO). Credit: CACI International Inc

A recently granted patent (Publication Number: US11914047B2) discloses a method for predicting Total Electron Content (TEC) in the ionosphere using a combination of a Long Short-Term Memory (LSTM) neural network and a Generative Adversarial Network (GAN) neural network. The method involves obtaining a dataset, preprocessing it by converting images to RGB arrays, inputting it into the ML model, training the model for at least 10 epochs, and predicting the TEC for a specified number of days. The prediction aims to improve performance in loss over the dataset and is specifically targeted for regions with a certain number of ground transmitters meeting a sparseness criterion. The method also includes determining signal delays and geolocating transmitters based on the predictions.

Furthermore, the patent claims involve additional steps such as separately training the LSTM and GAN networks before combining them, preprocessing steps like image extraction and scaling, and displaying the predicted TEC through a user interface. The method emphasizes the importance of training the model for a specific number of days to ensure accurate predictions during deployment. The performance improvement is measured using a root mean square (RMS) error criterion based on the comparison of color intensity in RGB arrays. Overall, the method provides a comprehensive approach to predicting TEC in the ionosphere, offering potential applications in various fields requiring precise location-based information and signal delay predictions.

To know more about GlobalData’s detailed insights on CACI International, buy the report here.

Premium Insights


The gold standard of business intelligence.

Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.


GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.

GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.