Burned Area Classification Based on Extreme Learning Machine and Sentinel-2 Images

Sentinel-2 satellite images allow high separability for mapping burned and unburned areas. This problem has been extensively addressed using machine-learning algorithms. However, these need a suitable dataset and entail considerable training time. Recently, extreme learning machines (ELM) have presented high precision in classification and regression problems but with low computational cost. This paper proposes evaluating ELM to map burned areas and compare them with other machine-learning algorithms broadly used. Several indices, metrics and training times were used to assess the performance of the algorithms. Considering the average of datasets, the best performance was obtained by random forest (DICE = 0.93; omission and commission = 0.08) and ELM (DICE = 0.90; omission and commission = 0.07). The training time for the best model was from ELM (1.45 s) and logistic regression (1.85 s). According to results, ELM was the best burned-area classification algorithm, considering precision and training time, evidencing great potential to map burned areas at global scales with medium-high spatial resolution images. This information is essential to fire-risk systems and burned-area records used to design prevention and fire-combat strategies, and it provides valuable knowledge on the effect of fires on the landscape and atmosphere.

Monitoring Small Water Bodies Using High Spatial and Temporal Resolution Analysis Ready Datasets

Basemap and Planet Fusion—derived from PlanetScope imagery—represent the next generation of analysis ready datasets that minimize the effects of the presence of clouds. These datasets have high spatial (3 m) and temporal (daily) resolution, which provides an unprecedented opportunity to improve the monitoring of on-farm reservoirs (OFRs)—small water bodies that store freshwater and play important role in surface hydrology and global irrigation activities. In this study, we assessed the usefulness of both datasets to monitor sub-weekly surface area changes of 340 OFRs in eastern Arkansas, USA, and we evaluated the datasets main differences when used to monitor OFRs. When comparing the OFRs surface area derived from Basemap and Planet Fusion to an independent validation dataset, both datasets had high agreement (r2 ≥ 0.87), and small uncertainties, with a mean absolute percent error (MAPE) between 7.05% and 10.08%. Pairwise surface area comparisons between the two datasets and the PlanetScope imagery showed that 61% of the OFRs had r2 ≥ 0.55, and 70% of the OFRs had MAPE <5%. In general, both datasets can be employed to monitor OFRs sub-weekly surface area changes, and Basemap had higher surface area variability and was more susceptible to the presence of cloud shadows and haze when compared to Planet Fusion, which had a smoother time series with less variability and fewer abrupt changes throughout the year. The uncertainties in surface area classification decreased as the OFRs increased in size. In addition, the surface area time series can have high variability, depending on the OFR environmental conditions (e.g., presence of vegetation inside the OFR). Our findings suggest that both datasets can be used to monitor OFRs sub-weekly, seasonal, and inter-annual surface area changes; therefore, these datasets can help improve freshwater management by allowing better assessment and management of the OFRs.

Hazardous area classification for wheat flour processing plant

Dust explosion possibly occurs in common unit operations such as mills, grinders, dryers, and other modes of transport. The basic element for the setting of hazardous zone types consist of identifies release sources, determination of classification region of hazardous area, overviewing the basic operation in wheat flour processing plant with their specification requirement and use of a suitable code or calculations to determine area scope. Therefore, this analysis can be more elaborate by classifying the hazardous area into several areas using the International Electro Technical Commission System for Certification to Standards Relating to Equipment for Use in Explosive Atmospheres standard. Thus, wheat flour processing plant area classification can be categorized according to three zones based on the quantity of an explosion into atmosphere and its release frequencies which are zones 20, zones 21, and zones 22. From the results, it can be summarized that zone 20 is almost inside or closer one with the main equipment located near the ignition source which could lead to dust explosion, whereas zone 21 and zone 22 comes after zone 20 which is a less hazardous area as compared to zone 20 areas.

TOD Typology Based on Urban Renewal: A Classification of Metro Stations for Ningbo City

In recent decades, the transit-oriented development (TOD) concept has been widely used all over the world, especially in China, for the massive construction of urban public transportation systems with rail transit as the backbone. However, it is not easy to make significant changes in a city while building a transportation system, and the transit-guided urban development expected by the TOD concept has not been completely realized. The transformation of nearby areas with the guidance of transit is also becoming the choice of many Chinese cities, especially for cities that have only had subways for a few years. Unlike other international metropolitan cities, with metro systems of considerable scale, the modernization process of most of the small and medium-sized cities in China is being carried out simultaneously with metro-based public transportation guidance. For cities which are still in their initial stage of the backbone public transportation system, there is not enough previous experience and evidence to support the suitability of TOD typological analysis based on the node-place model. More research based on the node-place model has also shown practical applications of the TOD in developed cities. However, there are very few studies that analyse cities in which rail transit and urban development are both in a period of rapid growth. The goal of this research is to identify which metro stations in these cities are suitable for TOD improvement and optimization. This article attempts to expand the willingness of residents on the basis of the traditional node-place model as one of the judgment indicators for evaluating whether existing stations and surrounding areas are suitable for TOD improvement. At the same time, traditional statistical analysis is combined with GIS and machine learning technology. Using this method, we propose the TOD improvement-oriented station area classification and identification method based on TOD typology theory. The results show that Ningbo's subway stations can be divided into four categories according to the suitability for TOD improvement, and we selected seven stations suitable for TOD improvement according to the characteristics of the node-place model. The practice in Ningbo has proved that this method is effective for identifying sites suitable for TOD improvement, especially for cities that have recently built subways.

GEOMORPHOLOGICAL MAPPING OF INTERTIDAL AREAS

Spatiotemporal geomorphological mapping of intertidal areas is essential for understanding system dynamics and provides information for ecological conservation and management. Mapping the geomorphology of intertidal areas is very challenging mainly because spectral differences are oftentimes relatively small while transitions between geomorphological units are oftentimes gradual. Also, the intertidal areas are highly dynamic. Considerable challenges are to distinguish between different types of tidal flats, specifically, low and high dynamic shoal flats, sandy and silty low dynamic flats, and mega-ripple areas. In this study, we harness machine learning methods and compare between machine learning methods using features calculated in classical Object-Based Image Analysis (OBIA) vs. end-to-end deep convolutional neural networks that derive features directly from imagery, in automated geomorphological mapping. This study expects to gain us an in-depth understanding of features that contribute to tidal area classification and greatly improve the automation and prediction accuracy. We emphasise model interpretability and knowledge mining. By comparing and combing object-based and deep learning-based models, this study contributes to the development and integration of both methodology domains for semantic segmentation.

Abstract 006: Predictors Of Establishing Outpatient Care Following A Heart Failure Hospitalization In Rural And Urban Dwelling Underserved Populations

Objective: The HRTSA (HeaRt Failure Transitional Services for Adults) clinic at the University of Alabama at Birmingham Hospital serves underinsured individuals with heart failure (HF). We examined the frequency and predictors of rural and urban dwelling individuals establishing care after a HF hospitalization. Methods: We included individuals ≥18 years of age referred to the HRTSA clinic after a HF hospitalization from 2016-2019. We used zip code of residence and the Rural-Urban Commuting Area classification system to define urban or rural. Urban zip codes have >30% of workers commuting to Census Bureau defined urbanized areas. We defined establishing care as attending the first clinic visit. Sociodemographic and clinical variables were collected at the time of referral and compared between groups using chi-square or t-tests as appropriate. Multivariable logistic regression was used to identify predictors of establishing care separately in urban and rural dwelling individuals. Results: Of 855 individuals referred to the HRTSA clinic after a HF hospitalization, mean age was 50±11 years, 15% were rural dwelling, 59% were African American (AA), and 32% were female. Rural dwelling individuals were less likely to establish care than their urban counterparts, although not statistically significant (71% vs. 77%; p=0.16). In rural dwelling individuals, AAs (OR 0.11, 95% CI 0.04-0.31), those with diabetes (OR 0.26, 95% CI 0.09-0.81), and current alcohol users (OR 0.25, 95% CI 0.08-0.83) had lower odds of establishing care; whereas in urban dwelling individuals, AAs (OR 2.75, 95% CI 1.65-4.59) and those with no insurance (OR 6.22, 95% CI 3.55-10.90) had higher odds of establishing care after multivariable adjustment (Table). Conclusions: We identified a significant disparity in AAs. Rural dwelling AAs with HF had lower odds of establishing care after a HF hospitalization, whereas urban dwelling AAs with HF had higher odds. Efforts to reduce this disparity are warranted to improve HF care in rural dwelling AAs.