Structural investigation of Zungeru-Kalangai fault zone and its environ, Nigeria using aeromagnetic and remote sensing data

Archimedes optimisation algorithm quantum dilated convolutional neural network for road extraction in remote sensing images

“…For instance, on the Massachusetts Road dataset, the AOA-QDCNNRE method gains a lower CT of 0.55s, whereas the CNN, U-Net, GL-Dense-U-Net, RDRCNN, and RDRCNN + post-process models obtain higher CT of 1.13s, 1.23s, 1.07s, 1.20s, and 0.98s respectively [ [26] , [27] , [28] ]. At the same time, in the GF-2 Road repository, the AOA-QDCNNRE method obtains a lesser CT of 0.17s, whereas the CNN, U-Net, GL-Dense-U-Net, RDRCNN, and RDRCNN + post-process approaches achieve superior CT of 0.95s, 0.88s, 1.02s, 1.08s, and 1.02s correspondingly [ [34] , [35] , [36] , [37] ].…”

Seismotectonic Stress Regime and Airborne-Gravity Lineament Investigation of the Caribbean region and its Kinematic implications

“…A low pass filter with cutoff wavenumber of 0.733 (wavelength of~1.364 km) was applied to the BA spectrum to accentuate the deep seated features and focus on mapping deep-seated regional-scale lineaments. The horizontal gradient magnitude (HGM) grid which provides a good estimation to enhance and delineate the signature of the geologic structures and lithologic boundaries (Nabighian, 1972;Blakely and Simpson, 1986;Awoyemi et al, 2017;Arogundade et al, 2022) was applied to the filtered residual field of the BA grid to delineate the deep-seated lineaments. Figure 5 illustrates the inferred tectonic lines of the Caribbean region.…”