Machine learning innovations in address matching: A practical comparison of word2vec and CRFs

Record linkage is a frequent obstacle to unlocking the benefits of integrated (spatial) data sources. In the absence of unique identifiers to directly join records, practitioners often rely on text‐based approaches for resolving candidate pairs of records to a match. In geographic information science, spatial record linkage is a form of geocoding that pertains to the resolution of text‐based linkage between pairs of addresses into matches and non‐matches. These approaches link text‐based address sequences, integrating sources of data that would otherwise remain in isolation. While recent innovations in machine learning have been introduced in the wider record linkage literature, there is significant potential to apply machine learning to the address matching sub‐field of geographic information science. As a response, this paper introduces two recent developments in text‐based machine learning—conditional random fields and word2vec—that have not been applied to address matching, evaluating their comparative strengths and drawbacks.     

A place for place: Modelling and analysing platial representations

This editorial presents a special collection of papers addressing the concept of place and its use in geographical information science (GIScience). The concept of place is a topic of increasing interest among GIScience scholars. First attempts to formalise platial information have been made and it is increasingly held that user‐generated data sets in particular are often more platial than spatial in nature. At the same time, and especially when compared to geometric spatial concepts, the concept of place is ambiguous, complex and difficult to capture in formal and analytical terms, suggesting the need for interdisciplinary approaches. This collection presents articles covering a wide range of place‐related aspects, including both conceptual and more applied contributions. In the present editorial we summarise these and comment on their individual contributions, and hope that the readership of Transactions in GIS will find the special collection inspiring and informative.     

Effect of organic complexation on the toxicity of Cu to the earthworm Eisenia fetida

The relationship between Cu speciation in solution and mortality and tissue Cu concentrations in Eisenia fetida was investigated. E. fetida were exposed to solutions containing 0.009, 0.049 and 0.125 mg Cu L⁻¹and 0, 0.15, 0.35 and 50 mg EDTA L⁻¹. Mortalities of 100, 60, 50 and 25% were recorded in the 0.125 mg Cu L⁻¹ solutions containing 0, 0.15, 0.35 and 50 mg EDTA L⁻¹, respectively. Similarly tissue body burden decreased with increasing EDTA concentration. Complexation capacity of the solution increased with EDTA concentration. In the 0.125 mg Cu L⁻¹ solution labile Cu concentration decreased with increasing EDTA concentration. These trends are attributed to complexation of free Cu ions with EDTA molecules, and the non-bioavailable nature of the resultant Cu–EDTA complex.     

CCD Photometry of KZ Hya using the 45-CM Telescope in Paraguay

A SX Phe-type pulsating variable KZ Hya (HD94033) was observed with CCD set attached to the 45-cm reflector at Asuncion Astronomical Observatory in Paraguay. In the present work, 12 maximum phases were covered. A new ephemeris has been obtained, and the result suggests a probable change of the pulsation period of KZ Hya.     

How much does dry‐season fog matter? Quantifying fog contributions to water balance in a coastal California watershed

The seasonally‐dry climate of Northern California imposes significant water stress on ecosystems and water resources during the dry summer months. Frequently during summer, the only water inputs occur as non‐rainfall water, in the form of fog and dew. However, due to spatially heterogeneous fog interaction within a watershed, estimating fog water fluxes to understand watershed‐scale hydrologic effects remains challenging. In this study, we characterized the role of coastal fog, a dominant feature of Northern Californian coastal ecosystems, in a San Francisco Peninsula watershed. To monitor fog occurrence, intensity, and spatial extent, we focused on the mechanisms through which fog can affect the water balance: throughfall following canopy interception of fog, soil moisture, streamflow, and meteorological variables. A stratified sampling design was used to capture the watershed's spatial heterogeneities in relation to fog events. We developed a novel spatial averaging scheme to upscale local observations of throughfall inputs and evapotranspiration suppression and make watershed‐scale estimates of fog water fluxes. Inputs from fog water throughfall (10–30 mm/year) and fog suppression of evapotranspiration (125 mm/year) reduced dry‐season water deficits by 25% at watershed scales. Evapotranspiration suppression was much more important for this reduction in water deficit than were direct inputs of fog water. The new upscaling scheme was analyzed to explore the sensitivity of its results to the methodology (data type and interpolation method) employed. This evaluation suggests that our combination of sensors and remote sensing allows an improved incorporation of spatially‐averaged fog fluxes into the water balance than traditional interpolation approaches.     

Bioenergetics of microbial sulfur-redox reactions in a glacial environment

The authors are studying microbial sulfur redox metabolisms in a glacial environment. The energy available from sulfur redox reactions at this site has been calculated using geochemical data obtained from the site. DNA has been extracted from the same site and is being analyzed for the presence and relative quantities of sulfur redox genes, to determine whether bioenergetic calculations can predict the sulfur redox reactions that microbes are in fact utilizing.     

Human damage assessments of coastal flooding for Hong Kong and the Pearl River Delta due to climate change-related sea level rise in the twenty-first century

Natural Hazards - The adverse impact of climate change-associated extreme weather events is becoming more significant globally, particularly the flood impact on coastal and low-lying areas such as...     

Geochemical Implications of Brine Leakage into Freshwater Aquifers

CO₂ injection into deep saline formations as a way to mitigate climate change raises concerns that leakage of saline waters from the injection formations will impact water quality of overlying aquifers, especially underground sources of drinking water (USDWs). This paper aims to characterize the geochemical composition of deep brines, with a focus on constituents that pose a human health risk and are regulated by the U.S. Environmental Protection Agency (USEPA). A statistical analysis of the NATCARB brine database, combined with simple mixing model calculations, show total dissolved solids and concentrations of chloride, boron, arsenic, sulfate, nitrate, iron and manganese may exceed plant tolerance or regulatory levels. Twelve agricultural crops evaluated for decreased productivity in the event of brine leakage would experience some yield reduction due to increased TDS at brine‐USDW ratios of < 0.1, and a 50% yield reduction at < 0.2 brine‐USDW ratio. A brine‐USDW ratio as low as 0.004 may result in yield reduction in the most sensitive crops. The USEPA TDS secondary standard is exceeded at a brine fraction of approximately 0.002. To our knowledge, this is the first study to consider agricultural impacts of brine leakage, even though agricultural withdrawals of groundwater in the United States are almost three times higher than public and domestic withdrawals.