Gemini Optimized

Best Gemini prompts for Astronomers

A specialized toolkit of advanced AI prompts designed specifically for Astronomers.

Professional Context

The pursuit of understanding the universe is hindered by the sheer volume of astronomical data, with scientists struggling to extract meaningful insights from petabytes of information. To make matters worse, the complexity of this data requires specialized tools and expertise, making it difficult for astronomers to focus on the science rather than the software. As a result, astronomers must develop innovative workflows to manage, analyze, and interpret the vast amounts of data generated by telescopes and spacecraft.

💡 Expert Advice & Considerations

Don't waste your time trying to use Gemini to replace your existing data analysis pipeline, instead use it to augment your workflow and focus on the high-level tasks that require human intuition and expertise.

Advanced Prompt Library

4 Expert Prompts
1

Spectral Analysis of Exoplanet Atmospheres

Terminal

Analyze the transmission spectra of the exoplanet K2-18b, using the publicly available data from the Hubble Space Telescope, to determine the presence of water vapor and methane in its atmosphere. Apply a Gaussian process regression model to the data, using a Matern kernel with a length scale of 10 Angstroms, to account for the correlations between the spectral channels. Then, use a Bayesian inference framework to estimate the posterior distribution of the atmospheric parameters, assuming a uniform prior distribution for the temperature and a log-uniform prior distribution for the pressure. Finally, compare the results to the existing literature and comment on the implications for our understanding of exoplanet atmospheres.

✏️ Customization:Replace K2-18b with the name of the exoplanet of interest and update the kernel and prior distributions accordingly.
2

Galaxy Morphology Classification

Terminal

Develop a deep learning model to classify the morphology of galaxies in the Sloan Digital Sky Survey (SDSS) dataset, using a combination of convolutional neural networks (CNNs) and recurrent neural networks (RNNs). Pre-process the images by applying a median filter to remove noise and normalizing the pixel values to the range [0, 1]. Then, train a CNN to extract features from the images, using a ResNet-50 architecture with a batch size of 32 and a learning rate of 0.001. Next, use an RNN to model the temporal dependencies between the features, using a long short-term memory (LSTM) network with 128 hidden units and a dropout rate of 0.2. Finally, evaluate the performance of the model using the SDSS galaxy morphology catalog and comment on the potential applications for galaxy evolution studies.

✏️ Customization:Replace the SDSS dataset with the desired galaxy survey and update the model architecture and hyperparameters as needed.
3

Gravitational Lensing Mass Reconstruction

Terminal

Reconstruct the mass distribution of the galaxy cluster Abell 1689, using the strong lensing data from the Hubble Space Telescope and the weak lensing data from the Subaru Telescope. Apply a non-parametric method, such as the PixeLens algorithm, to the strong lensing data to constrain the mass distribution in the central region of the cluster. Then, use a parametric method, such as the Navarro-Frenk-White (NFW) profile, to model the mass distribution in the outer region of the cluster. Finally, combine the strong and weak lensing data using a Bayesian framework to estimate the posterior distribution of the mass parameters, assuming a uniform prior distribution for the concentration parameter and a log-uniform prior distribution for the mass scale.

✏️ Customization:Replace Abell 1689 with the name of the galaxy cluster of interest and update the lensing data and model parameters accordingly.
4

Time Series Analysis of Stellar Variability

Terminal

Analyze the light curve of the variable star RR Lyrae, using the publicly available data from the Kepler Space Telescope, to determine the periodicity and amplitude of its variability. Apply a Lomb-Scargle periodogram to the data to identify the significant periodic components, using a false alarm probability (FAP) threshold of 0.01. Then, use a Gaussian process regression model to reconstruct the continuous light curve, assuming a squared exponential kernel with a length scale of 10 days. Finally, comment on the implications of the results for our understanding of stellar evolution and the potential applications for exoplanet hunting.

✏️ Customization:Replace RR Lyrae with the name of the variable star of interest and update the kernel and FAP threshold accordingly.