This paper introduces the idea of using deep fully convolutional neural networks for pixel-level defect detection in concrete infrastructure systems. Although coarse patch-level deep learning crack detection models abound in the literature and have shown promise, the coarse level of detail provided, together with the requirement for fixed-size input images, significantly detract from their applicability and usefulness for refined damage analysis. The deep fully convolutional model for crack detection introduced in this paper (CrackPix) leverages well-known image classification architectures for dense predictions by transforming their fully connected layers into convolutional filters. A transposed convolution layer is then used to upsample and resize the resulting prediction heatmap to the size of the input images, thus providing pixel-level predictions. To develop and train these models, a concrete crack image data set was collected and carefully annotated at the pixel level and was then used to train the model. Sensitivity analysis showed that CrackPix was capable of correctly detecting over 92% of crack pixels and 99.9% of noncrack pixels in the validation set. The model performance was then compared against a state-of-the-art patchwise model, as well as traditional edge detection and adaptive thresholding alternatives, and its advantages were illustrated. The success of CrackPix, which enables the quantification of crack characteristics (e.g., width and length) in concrete structures, provides a key step toward automated inspection and quality assurance for infrastructure in future smart cities.

The functionality of the U.S. transportation infrastructure system is dependent upon the health of an aging network of over 600,000 bridges, and agencies responsible for maintaining these bridges rely on the process of load rating to assess the adequacy of individual structures. This paper presents a new approach for safety screening and load-capacity evaluation of large bridge populations that seeks to uncover heretofore unseen patterns within the National Bridge Inventory database and establish relationships between select bridge attributes and their load-capacity status. Decision-tree and random-forest classification models were trained on the national concrete slab bridge data set of over 40,000 structures. The resulting models were validated on an independent data set and then compared with a number of existing judgment-based schemes found in an extensive survey of the current state of practice in the United States. The proposed approach offers a method that provides guidance for improved allocation of resources by informing maintenance decisions through rapid identification of candidate bridges that require further scrutiny for either possible load restriction or restriction removal.

Accurate estimation of fuels is essential for wildland fire simulations as well as decision-making related to land management. Numerous research efforts have leveraged remote sensing and machine learning for classifying land cover and mapping forest vegetation species. In most cases that focused on surface fuel mapping, the spatial scale of interest was smaller than a few hundred square kilometers; thus, many small-scale site-specific models had to be created to cover the landscape at the national scale. The present work aims to develop a large-scale surface fuel identification model using a custom deep learning framework that can ingest multimodal data. Specifically, we use deep learning to extract information from multispectral signatures, high-resolution imagery, and biophysical climate and terrain data in a way that facilitates their end-to-end training on labeled data. A multi-layer neural network is used with spectral and biophysical data, and a convolutional neural network backbone is used to extract the visual features from high-resolution imagery. A Monte Carlo dropout mechanism was also devised to create a stochastic ensemble of models that can capture classification uncertainties while boosting the prediction performance. To train the system as a proof-of-concept, fuel pseudo-labels were created by a random geospatial sampling of existing fuel maps across California. Application results on independent test sets showed promising fuel identification performance with an overall accuracy ranging from 55% to 75%, depending on the level of granularity of the included fuel types. As expected, including the rare—and possibly less consequential—fuel types reduced the accuracy. On the other hand, the addition of high-resolution imagery improved classification performance at all levels.

A novel Portable L-band radiometer (PoLRa), compatible with tower-, vehicle- and drone-based platforms, can provide gridded soil moisture estimations from a few meters to several hundred meters yet its retrieval accuracy has rarely been examined. This study aims to provide an initial assessment of the performance of PoLRa-derived soil moisture at a spatial resolution of approximately 0.7 m × 0.7 m at a set of sampling pixels in central Illinois, USA. This preliminary evaluation focuses on (1) the consistency of PoLRa-measured brightness temperatures from different viewing directions over the same area and (2) whether PoLRa-derived soil moisture retrievals are within an acceptable accuracy range. As PoLRa shares many aspects of the L-band radiometer onboard NASA’s Soil Moisture Active Passive (SMAP) mission, two SMAP operational algorithms and the conventional dual-channel algorithm (DCA) were applied to calculate volumetric soil moisture from the measured brightness temperatures. The vertically polarized brightness temperatures from the PoLRa are typically more stable than their horizontally polarized counterparts across all four directions. In each test period, the standard deviations of observed dual-polarization brightness temperatures are generally less than 5 K. By comparing PoLRa-based soil moisture retrievals against the simultaneous moisture values obtained by a handheld capacitance probe, the unbiased root mean square error (ubRMSE) and the Pearson correlation coefficient (R) are mostly below 0.05 m³/m³ and above 0.7 for various algorithms adopted here. While SMAP models and the DCA algorithm can derive soil moisture from PoLRa observations, no single algorithm consistently outperforms the others. These findings highlight the significant potential of ground- or drone-based PoLRa measurements as a standalone reference for the calibration and validation of spaceborne L-band synthetic aperture radars and radiometers. The accuracy of PoLRa-yielded high-resolution soil moisture can be further improved via standardized operational procedures and appropriate tau-omega parameters.