Measurement-while-drilling (MWD) data recorded from drill rigs can provide a valuable estimation of the type and strength of the rocks being drilled. Typical MWD sensors include bit pressure, rotation pressure, pull-down pressure, pull-down rate, and head speed. This letter presents an empirical comparison of the statistical performance, ease of implementation, and computational efficiency associated with three machine-learning techniques. A recently proposed method, boosting, is compared with two well-established methods, neural networks and fuzzy logic, used as benchmarks. MWD data were acquired from blast holes at an iron ore mine in Western Australia. The boreholes intersected a number of rock types including shale, iron ore, and banded iron formation. Boosting and neural networks presented the best performance overall. However, from the viewpoint of implementation simplicity and computational load, boosting outperformed the other two methods.

Several environmental and sensor effects make the determination of the wavelength position of absorption features in the visible near infrared (VNIR) (400-1200 nm) from hyperspectral imagery more difficult than from nonimaging spectrometers. To evaluate this, we focus on the ferric iron crystal field absorption, located at about 900 nm (F900), because it is impacted by both environmental and sensor effects. The consistency with which the wavelength position of F900 can be determined from imagery acquired in laboratory and field settings is evaluated under artificial and natural illumination, respectively. The wavelength position of F900, determined from laboratory imagery, is also evaluated as an indicator of the proportion of goethite in mixtures of crushed rock. Results are compared with those from a high-resolution field spectrometer. Images describing the wavelength position of F900 showed large amounts of spatial variability and contained an artifact-a consistent shift in the wavelength position of F900 to longer wavelengths. These effects were greatly reduced or removed when wavelength position was determined from a polynomial fit to the data, enabling wavelength position to be used to map hematite and goethite in samples of ore and on a vertical surface (a mine face). The wavelength position of F900 from a polynomial fit was strongly positively correlated with the proportion of goethite (R ² =0.97). Taken together, these findings indicate that the wavelength position of absorption features from VNIR imagery should be determined from a polynomial (or equivalent) fit to the original data and not from the original data themselves.

Classification of aerial imagery has been one of the central tasks in many remote sensing applications, e.g., environmental assessment and monitoring, city planning, and land cover change detection. Typical methods for classifying these types of images follow a bottom-up approach in which information is processed sequentially from pixel-to-object level. Pixel-wise image processing techniques are suitable for aerial images with a lower spatial resolution, where the region of interest includes natural terrains of a large area of, for example, forests, water bodies, grass, and tree canopies. With the advance in sensor technology, very-high-resolution (VHR) aerial images are now readily available and enable the extraction of fine details with a ground spatial resolution of about 10 cm. Using VHR aerial imagery, state-of-the-art deep learning and structured prediction methods can be utilized to generate dense semantic segmentation. For instance, methods based on Markov random fields (MRFs) for classification¹ 2. 3. ^{– 4} have been proposed to perform land cover mapping utilizing the enhanced spatial contextual information in VHR images.