Browse Articles

The authors studied the ability of deep learning models to predict droughts in the midwestern United States.

Here, in an effort to develop a model to predict future groundwater levels, the authors tested a tree-based automated artificial intelligence (AI) model against other methods. Through their analysis they found that groundwater levels in Texas aquifers are down significantly, and found that tree-based AI models most accurately predicted future levels.

Here, recognizing the difficulty associated with tracking the progression of dementia, the authors used machine learning models to predict between the presence of cognitive normalcy, mild cognitive impairment, and Alzheimer's Disease, based on blood DNA methylation levels, sex, and age. With four machine learning models and two dataset dimensionality reduction methods they achieved an accuracy of 53.33%.

Here the authors sought to use three machine learning models to predict poverty levels in Cambodia based on available household data. They found teat multilayer perceptron outperformed the other models, with an accuracy of 87 %. They suggest that data-driven approaches such as these could be used more effectively target and alleviate poverty.

The authors looked at the feasibility to predict wind speeds that will have less reliance on using historical data.

The authors looked at the ability to use audio clips to analyze the progression of Parkinson's disease.

Cystic fibrosis is a genetic disease caused by mutations in the CFTR gene. In this paper, the authors attempt to identify variations in stretches of up to 8 nucleotides in the protein-coding portions of the CFTR gene that are associated with disease development. This would allow screening of newborns or even fetuses in utero to determine the likelihood they develop cystic fibrosis.

To address the limitations in predicting the severity of Atrial Septal Defect (ASD), here the authors utilized a fluid-filled chamber model to quantify the relationship between defect size and right atrial fluid output. The findings confirmed that larger ASD diameters result in a linear increase in fluid output, validating a cost-effective model that can improve clinical prognosis and treatment planning for heart failure risks.

Here, the authors investigated the integration of large language models (LLMs) with drug target affinity predictors (DTAPs) to improve drug repurposing, demonstrating a significant increase in prediction accuracy, particularly with GPT-4, for psychotropic drugs and the sigma-1 receptor. This novel approach offers to potentially accelerate and reduce the cost of drug discovery by efficiently identifying new therapeutic uses for existing drugs.

Dust accumulation on solar panels can reduce electricity output by 20–50%, posing a major challenge for solar energy collection. Instead of altering panel design, we explored a simpler approach by modifying surface energy through nanotexturing, predicting that hydrophobic surfaces would repel both water and dust. This study found that treating glass and silicone surfaces with potassium hydroxide (KOH) for 13 and 10 minutes, respectively, created optimal nanotextures (445 nm for glass, 205 nm for silicone), significantly reducing dirt accumulation and improving solar energy capture.