Deep learning heavily relies on statistical correlations to drive artificial intelligence (AI) innovations, particularly in computer vision applications like autonomous driving and robotics. However, despite providing a solid foundation for deep learning, these statistical correlations can be vulnerable to unforeseen and uncontrolled factors. The lack of prior knowledge guidance can result in spurious correlations, introducing confounding factors and affecting the model's robustness. To address this challenge, recent research efforts have focused on integrating causal theory into deep learning methodologies. By modelling the inherent and unbiased causal structure, causal theory can potentially mitigate the impact of spurious correlations effectively. Hence, this paper explores the basics of causal methodologies in image classification.

Organisms release their nucleic acid in the environment including the DNA and RNA which can be used to detect their presence. eDNA/eRNA techniques are being used in different sectors to identify organisms from soil, water, air, and ice since long. The advancement in technology led to easier detection of different organisms without impacting the environment and the organism itself. These methods are being employed in different areas including surveillance, history, and conservation. eDNA and eRNA methods are being extensively used in aquaculture and fisheries setting to understand the presence of different fish species and pathogens in water. However, there are some challenges associated with the reliability of the results because of the degradation of nucleic acid by several factors. In aquaculture there are several diseases and parasites detected with these methods. In this review we discuss different aquaculture diseases and parasites detected with eDNA/eRNA approach and the fate of these nucleic acids when subjected to different water quality and environmental parameters. This review intends to help the researcher about the potential of eDNA/eRNA based detection of pathogens in aquaculture; this will be useful to predict the potential outbreak before it occurs. Along with that this paper intends to make people understand several factors that degrade and can hamper the detection of these nucleic acids.

The current paper aims to study the impact properties of additively manufactured Maraging steel (1.2709) using laser powder bed fusion (PBF-L) processing. The specimens were manufactured using 3Dsystems ProX 300 equipment under constant specific power input, or Andrew Number. The interactions between the build strategy and parameters, such as Hatch spacing and Scan speed was, and the impact strength and fracture were investigated. The Impact energy anisotropy was also investigated parallel and perpendicular to the build direction. Instrumented impact testing was performed, and the fractography supported that the fusion zone geometry dictated the fracture behaviour. The influence from gaseous elements such as Nitrogen, Oxygen and Hydrogen was found insignificant at the levels found in the printed material.