Archive for the ‘General’ Category

Thoughts on ” Scaling Behavior of Human Mobility Distributions”

Sunday, November 3rd, 2019

This paper presented an empirical study of how temporal and spatial scale impacts the distribution of mobility data. The main finding is not surprising – a different spatial and temporal scale of analysis leads to a different distribution of data. Once again we saw the importance of scale in the analysis of the spatial datasets.

What interests me are finding 3 and 5. Finding 3 states that ordering between metrics over datasets is generally preserved under resampling, which implicates that the comparison across the datasets can be made regardless of the spatial and temporal resolution. This reminds me of the reading of spatial data quality. Though it is critical about the effects of scale, it is also important to bear in mind about the “use”. In the case of comparing human mobility across different datasets, the scale does not seem to matter anymore.

Find 5 concludes that the sensitivity to resampling can itself be a metric. I think this is a good point but I was having some difficulties to grasp what the authors want to express in the subsequent argument of “difference in sensitivity indicates that information about population mobility is encoded in the scaling behavior”. I think they could have explained this better. To my understanding, the difference in sensitivity to resampling is nothing more than the difference in the heterogeneity of the datasets.

Another point I want to make is that although the analysis is performed on mobility datasets, it seems to me that the most conclusions they made can be generalized to all kinds of datasets. I’m not sure what is special about the mobility data here in their analysis.

Thoughts on “Miller et. al – Towards an integrated science of movement”

Sunday, November 3rd, 2019

“Towards an integrated science of movement” by Miller et. al lays out the advances that have been made in the understanding of mobility and movement as a whole given the growth of location-aware technologies, which have provided much more accessible data acquisition. They are interested in synergizing the components of animal movement ecology and human mobility science to promote a science of movement.

In regards to mobile entities that are defined as “individually identifiable things that can change their location frequently with respect to time”, are there specific definitions that clearly define what “frequently in time” means? Examples have been made with birds or humans, but would trees or continental masses be considered mobiles entities as well?

It would be interesting to assess the impact of tracking location on the observations, in other words if tracking can affect the decisions made by whoever or whatever is being tracked. For example, a human who knows they are being tracked might change their trajectory solely based on the fact they do not want to potentially compromise sensitive areas or locations they visit, while an animal could behave differently if the technology used to track its movement make it more visible to predators. There is an ethical dilemma in tracking a human being without their consent, but it must be acknowledged that tracking does come with some consequences in terms of results differing from reality.

Reflecting on “Scaling Behavior of Human Mobility Distributions”

Sunday, November 3rd, 2019

Analyzing big data is an obstacle across GIS, and movement is no exception. Cutting out potentially unnecessary components of the data in order to reduce the dataset  is one way of addressing this challenge. In Paul et al.’s piece they look at how much cutting down on datasets’ time windows may affect the end distribution.

Specifically, they examine the effects of changing the spatio-temporal scale of five different movement datasets, revealing which metrics are best to compare human relationships to movement across datasets. The findings of the study, which examines GPS data from undergraduate students, graduate students, schoolchildren, and working people, reveal that changing temporal sampling periods does affect the distributions across datasets, but the extent of this change is reliant on the dataset.

After reading this piece, I would like to understand more about how researchers studying movement address privacy. I’m sure having enormous datasets of anonymized data addresses part of this issue; however, I’m sure different government agencies, organizations, corporations, etc. collecting this data have different standards regarding the importance of privacy. How strictly enforced are data privacy laws (looking at movement data specifically)? 

Thoughts on “Fisher et. al – Approaches to Uncertainty in Spatial Data”

Sunday, November 3rd, 2019

This article by Fisher et. Al clearly lays out the components and concepts that are part of spatial data uncertainty and explain solutions that have been proposed to counteract their potential consequences on data analysis and interpretation. A better understanding of what uncertainty really is helped me realize that an overwhelming majority of geographical concepts are poorly defined objects, either being vague or ambiguous.

One solution for reducing the effects of discord ambiguity, although maybe not realistic but very practical, would be to create a global lexicon that stipulates how certain statistics need to be calculated and defines concepts on a global scale. This would allow for easier comparisons between regions currently using different approaches and would uniformize the process. However, it is important to note that this could not be applied to every statistical measurement, definition or observations made given the fact there could be biases against certain regions. An example could be that a road is conceptualized differently in one part of the world when compared to another.

On the topic of data quality, the advent of geolocational technologies has propelled geospatial data to the forefront of organizations and businesses aiming to profit from their use. Without trying to be too cynical, wouldn’t private organizations have an incentive to manipulate the data quality at the detriment of others in order to benefit themselves? This is where Volunteered Geographic Information (VGI), an example being OpenStreetMap, comes into play as to balance the playing field, in this case being Google Maps.

Thoughts on “Spatial Data Quality”

Sunday, November 3rd, 2019

The authors did a good job summarizing the concepts related to spatial data quality in terms of the definitions and the types and sources of error. Although I do not completely agree with the starting statement of “geospatial data are a model of reality”, I do agree that all geospatial data are imprecise, inaccurate, out of data, and incomplete” at different levels. The question for researchers is that to what degree such impreciseness, inaccuracy, outdatedness, and incompleteness should be either accepted or rejected, and how do we assess the data quality. The authors presented the concepts of internal and external quality, where the internal quality refers to the similarity between the data produced and the perfect data should have been produced, and the external quality refers to the “fitness for use” or “fitness for purpose”. I would argue that external quality should be the metric to look at. However, as the authors stated, there is very little evaluation method for external quality. I think this is because of the “non-absoluteness” and “relativeness” properties of the external quality. It seems to be that a case-by-case assessment approach is needed depending on what the “use” is. I’m curious to know if there is a generalized way of doing this. Moreover, with geospatial data coming from different sources such as VGI, crowdsourcing, sensors, etc., the uncertainties are intensified, whereas they provide more opportunities “for use”. I think coming up with ways to assess the external quality is of vital importance.

Thoughts on “Spatial Data Quality: Concepts”

Saturday, November 2nd, 2019

This chapter begins with the quote “All models are wrong but some are useful”, which I believe sums up the article fairly succinctly, as it addresses the constant imprecise, inaccurate, incomplete, and outdated nature of GIS data. This reminds me of when we discussed non-ideal data from last week’s Openshaw (1992) paper; however, this piece explains it in much more detail than Openshaw, relating it back to external and internal data quality differences and data representation challenges. 

Since the rise in popularity of the internet and user-generated content, there is a lot more concern towards accessing data quality and accuracy. I have been conducting a bit of research on VGI, as that is my research topic, and data accountability and accuracy are huge concerns in that field. Much like differing definitions of quality given here, there is no one correct way to access accuracy. It is all reliant on the type of data being extracted and researched, and the motives for collecting such data. For instance, if a project was collecting user-generated data concerning users’ perceptions of a place, then accuracy does not matter, whereas in OpenStreetMap, for example, there is a team of moderators carefully watching and reviewing users’ inputs, as accuracy is a top priority. Thus, I think the motives for the research, specifically whether the researcher is looking for more accurate data, more precise data, or both, is a very important component to address when examining spatial data quality. 

This topic also reminds me of when we discussed open government data and how there is often not consistent data throughout each department, i.e. the formatting of the data, the original scale of the data, etc. does not usually match across departments, thus challenging the quality of the end result. I worked on a GIS project last semester analyzing water quality levels and ran into quite a few hiccups when I realized there were many months and years missing from the data sets I was trying to analyze. In hindsight, I should have examined the spatial data quality of the data I was planning to use more before starting my research.

Overall, I think this chapter does a good job of explaining the complexity of spatial data quality and the errors inherent to geospatial research.

Thoughts on Research Challenges in Geovisualization

Monday, October 28th, 2019

This article gives us a detailed introduction about Geovisualization. The author started by giving out reasons about whys should we care about Geovisualization. In short, I think the explanation would be that people can get knowledge from it by transforming the geospatial referenced data into information and turn the information into knowledge by analysing it. One example would be the switching from data to paper maps, and then paper maps to web-based maps. The visualization is advancing overtime, so researcher can get more out of a geospatial dataset. How much can we get from the dataset are largely depends on the visualizing techniques.

Then, the author introduced some issues that still remains in the geovisualization field. These problems are representation, visualization-computation integration, interface design, and cognition-usability. One issue I noticed about representation is that in order to take full advantage of the information we want to give out in the geospatial dataset, we want to personalized representation as much as possible. One example I can think of is about Google Map. When I’m trying to find certain stores in a big shopping mall, I always find it hard to locate a certain floor and the direction since sometimes there is no detailed information about this represented on the map. However, I find some other map application gives about 3D navigations in shopping mall so user will find it very easy to locate a certain store. Obviously, the latter application gets more out of the mall database, and make the navigation process more personalized.

Thoughts on GeoAI (Openshaw,1992)

Monday, October 28th, 2019

This article essentially introduced the emergency of GeoAI. The author gives out some detailed reasons about why we should use GeoAI, and he also briefly reviews the expert systems approaches, the use of heuristic search procedures, and the utility of neurocomputing based tools. At last, he predicted the future trends of GeoAI as a emerging new technology.

GeoAI is actually a new topic to me since I have never done a project using this technique. I think it would be very useful and convenient when we are facing a huge dataset and trying to analyse or model it. As far as I understand it, people basically just transfer their thoughts to the computer and let the computer to decide and calculate result. Then, there would be a point where GeoAI will be connected to spatial data uncertainty. Is it possible to train the data and let it decide the level of uncertainty in a dataset? Or it there any way to eliminate of reduce some uncertainty in a dataset?

Another aspect to think about the uncertainty problem in GeoAI would be the supervision of human. What I get from the article is that people can supervise the computer when they are doing analytic works using the algorithms researchers put in. Would this supervision process bring more uncertainty into the dataset, or it will help to reduce the error? These are thoughts that come to me when I’m reading the article.

Research Challenges in Geovisualization (MacEachren & Kraak, 2001)

Sunday, October 27th, 2019

In this paper, Maceachren and Kraak (2001) concluded the research challenges in geovisualization. The first thing that catches my eye is the cartograph cube, which defines visualization in terms of map use. The authors argue that visualization is not the same thing as cartography. Visualization, same as communication is not just about making maps, but is also using them.

While the authors highlight the importance of scale issue, integrating heterogeneous data also present a challenge for geovisualization, because of the different categorization schemes and complex semantics that are applied in data creation. Similar conditions or entities are often represented with different attributes or measured with varying measurement systems. Therefore, the heterogeneity raises questions when we use data from different data producers: How to assess heterogeneity? How to make decisions about whether data may be combined? How to integrate multiple data sets if the same semantics are used differently?

Further, the emergence of geospatial big data, such as millions of conversations via location-enabled social media, stretches the limits of what and how we map. The potential of using geospatial big data as a data source for geovisualization requires developing appropriate methodologies. While this paper mainly discusses geovisualization of quantitative data. I am also curious about how to visualize qualitative spatial data. (QZ)

Thoughts on “Koua et. al – Evaluating the usability of visualization methods in an exploratory geovisualization environment”

Sunday, October 27th, 2019

This article by Koua et. al articulates that the choices made and the techniques used when designing a geovisualization are crucial to convey all the necessary information to the interpreter. Based on certain objectives, certain visualizations were more effective at conveying the necessary information and were more usable compared to others, something that was tested with scientists in the field.

An interesting addition to the research would have been to test the geovisualizations with non-scientists given the fact they are becoming increasingly present in interactive newspaper articles online and on websites in general: what is easily conveyed to scientists may not be as easy to a general public. This research reinforced the notion that these visualizations are only used by professionals in the field, which is no longer the case. In an era where misinformation is rampant on social media and online, understanding how certain geovisualizations are interpreted by the general public could certainly help in designing more intuitive geovisualization techniques.

Technological advancements in the coming years will potentially open the door for new visualization techniques, which, for example, could make use of augmented reality and other emerging technologies. This could make it easier to visually represent certain situations and aid in the transfer of information.

Thoughts on Vopham “Emerging trends in geospatial artificial intelligence (geoAI)”

Sunday, October 27th, 2019

The article by Vopham et. al Emerging trends in geospatial artificial intelligence (geoAI) Potential applications for environmental epidemiology provides us with a general understanding of what geoAI is and how it is utilized.

The interdisciplinary nature of geoAI is highlighted not only by the scientific fields that develop and utilize geoAI, but also by the wide spectrum of applications “to address real-world problems” it has. These vary from predictive modeling of traffic to environmental exposure modeling. Focus on machine learning, data mining, big data and volunteered geographic information has helped the expansion of geoAI. The main topic of this paper, however, is how this scientific discipline can be applied to the advancement of environmental epidemiology.

I find the future possibilities and applications of geoAI particularly exciting. As explained in the article, the progress in geoAI that has allowed for more accurate, high-resolution data which has the potential to revolutionize the use of remote sensing.  As with most of the evolving GIScience technologies we have yet to uncover their full potential and applications.

Thoughts on Koua “Evaluating the usability of visualization methods in an exploratory geovisualization environment”

Sunday, October 27th, 2019

The article Evaluating the usability of visualization methods in an exploratory geovisualization environment by Koua et al. report on their findings regarding visualization methods and geovisualization. The study aimed to evaluate how the use of different visualization tools impacted the usability and understanding of geospatial data.

I found it quite interesting to see the results of the study, out of six different ways of visualizing the same data, the map was found to be the better tool for tasks such as locating, ranking and distinguishing attributes. On the other hand, the self-organizing map (SOM) component plane was better for the visual analysis of relationships and patterns in the data. This brings a question to mind about the type of users interacting with the product.

In the study, the participants were made up of 20 different individuals with a background in GIS and data analysis. This means that they had experience with GIS tools and their own preference of tools for analysis – they knew what to expect and (generally) how to use the tools. I wonder how the results would change if the participants of the study varied more in their knowledge background of GIS. How would someone with no particular experience with GIS tools interact and understand that same data? I find this particularly interesting because when creating a Geoweb product for public use that supports analysis, the user interaction and understanding of the product is crucial.

Reflection on “Research Challenges in Geovisualization”

Sunday, October 27th, 2019

This piece gives a very thorough background on geovisualization and its problems, especially its problems across disciplines.

A part of the piece that caught my attention was when MacEachren and Kraak said that “Cartographers cannot address the problem alone.” Through all the papers we have read in this class, there is a trending theme that there needs to be more cross-disciplinary communication in GIS to solve crosscutting problems. This article is better than other articles who just mention that more communication needs to happen; this article actually lists ways to better research cross-disciplinarily, in addition to listing short, medium, and long term goals. 

Although, I also feel that this article was written in a way that was very very generalized and vague, which made it a bit difficult to follow. This also gave their reasons less clout because it’s always easier to explain vague solutions as opposed to more specific ones. Some specific GIS examples would have also been very helpful!

The potential of AI methods in GIS (Openshaw, 1992)

Sunday, October 27th, 2019

In this old paper, Openshaw (1992) calls attention to the potential of artificial intelligence (AI) methods in relation to spatial modeling and analysis in GIS. He argues that GIS with a low level of intelligence has only little changes to provide efficient solutions to spatial decision-making problems. The application of AI principles and techniques may provide opportunities to meet the challenges encountered in developing intelligent GIS. One thing which draws my attention is that the author mentions it is important to “discover how best to model and analyse what are essentially non-ideal data”. But I didn’t see a definition or explanation of non-ideal data in this paper. Does the non-ideal data refer to less structured data or unreliable data? AI can use less structured data such as raster data, video, voice, and text to generate insights and predictions. However, every AI system needs reliable and diverse data to learn from. Very similar data can lead to overfitting the model, with no new insights.

Further, Openshaw demonstrates the usefulness of artificial neural networks (ANNs) in modeling spatial interaction and classifying spatial data. But he didn’t mention how to transfer data from the GIS to the ANN and back. The most widely used ANNs requires data in raster form. However, the spatial data used to produce an interpretive result in GIS is most efficiently managed in vector form. Therefore, I am wondering if there is an efficient methodology to transfer information between the GIS and the ANN.

As of now, GIScience is not new to AI. For example, the most well-known application of AI is probably image classification, as implemented in many commercial and open tools. Many classification algorithms have been introduced to clustering and neural networks. Also, recent increases in computing power have made AI systems efficiently deal with large amounts of input data. I am looking forward to learning more about the current uses of AI in GIS.

Thoughts on “VoPham et. al – Emerging trends in geospatial artificial intelligence (geoAI)”

Sunday, October 27th, 2019

In “Emerging trends in geospatial artificial intelligence (geoAI)”, VoPham et. al explain the emergence of geoAI as a new research field combining concepts, methods and innovations from various fields, such as spatial science, artificial intelligence (AI), data mining and high performance computing, and give examples of recent applications in real-life situations. The fusion between AI and GIS helps us obtain more accurate representations compared to traditional methods given the ability to make use of spatial big data.

As mentioned in the article, geoAI has the ability to revolutionize remote sensing, with the potential to more accurately recognize earth features. Slight differences in the spectral response of a pixel could be detected by an algorithm trained to detect these ever so small differences, which could help detect and respond to forest fires more rapidly for example. A research project I worked on last year aimed at assessing the extent of the Fort McMurray forest fire of 2016, and although the results were extremely similar to what had been obtained by official government sources, the use of geoAI could have overcome the limitations of the NDVI and NBRI indices used.

As with any new emerging scientific field, it will be interesting to see how and to what geoAI will be applied to next. An example would be spatial Agent-based modelling (ABM), which aims to simulate the actions of specifically defined agents in space, which could highly benefit from geoAI and the input from spatial big data. Geographical ontologies could also be redefined by deep learning, which could conceptualize things differently from the way we currently do.

Thoughts on “Evaluating the usability of visualization methods in an exploratory geovisualization environment”

Sunday, October 27th, 2019

There’s a very important component of geovisualization missing from this article: aesthetics. Koua et al cover a great number of factors important to geovisualization, in particular test measures, effectiveness, and usability. However, they only briefly mention users’ “subjective views” towards a geovisualization and “compatability (between the way the tool looks… compared with the user’s conventions and expectations).” This omission is noticeable, since geovisualization is, as its name implies, a very visual aspect of any cartographic scheme, and the aesthetics of any visualization are almost always inherently important. However, it may not be entirely surprising, since this paper focuses on the “usability and usefulness of the visual-computational analysis environment.” The authors have implied through this omission that aesthetics do not relate to the usability and usefulness of geovisualization; however, I would disagree with that assumption. Maps are, at their core, a visual way of displaying data; how they look, not just how they show data, matter. Therefore, however subjective aesthetics are (and they are quite subjective), they must relate to the effectiveness of a map. A map could have great data to show, but if the colors are oversaturated, or the water isn’t blue, this could distract the eye of whoever is looking at it and take away from the map’s findings. If the map user can’t pull the important information from it, then what’s the point of having a map at all? I understand why the authors may have decided to omit aesthetics, considering it’s such a subjective factors compared to everything else they discuss; however, including aesthetics would have made this discussion on visualization usability more robust and complete.

Thoughts on “Emerging Trends in geoAI” by VoPham et al

Sunday, October 27th, 2019

This article is extremely relevant to the independent study I’m conducting this year, and I think I’ll be able to use it for some of the methods I’m conducting. My study is looking at different 911 calls in Baltimore over the last 7 years (assaults, overdoses, car accidents, person found not breathing, and shootings). I have both the address where the call was placed as well as the time, down to the minute. This could be considered a “health” study of sorts, since bodily harm is a health outcome, and I’d like to find factors that correlate to the calls’ times and locations. Therefore, the geoAI described in this article would be great for my study. It tackles big data, which I have (over 6.5 million 911 call times and locations), geoAI that produces high-resolution exposure modeling, which is what I’m looking for. The example given about the study that developed a method to predict air pollution was particularly appealing to me. I’d like to do something similar with my own data, inputting as much spatial data available (demographic indicators, built environment factors, etc) to see which variables predict calls in space and time. I’m glad that this article discusses “garbage in, garbage out computer science,” as that was an issue I was concerned about while reading this piece: that treating geoAI like a black box or ignoring data quality because advanced methods are applied to them may result in flawed results. These are factors I’ll have to keep in mind in my own study, and I’ll have to research further than this article on the proper data, methods and contexts to conduct such an exposure analysis.

Thoughts on “Some Suggestions…” by Stan Openshaw (1992)

Saturday, October 26th, 2019

Openshaw’s paper, written in the early 1990s, gives us an interesting glimpse into the early days of GIS. It was very interesting to hear about the problems of then as compared to the problems of today; for instance, he advocates that computers should be utilized more in analyzing GIS data, which is in comparison to today, where computers are ubiquitous in GIS analysis. This paper focuses on greater AI involvement because he believes the combination of non ideal data that GIS provides and the increasing complexities in GIS research make some analysis too complex for people to understand.

Openshaw believes that we must shift our mindsets from prioritizing the conservation of computer energy to the utilization of computer’s “endless” energy. He expands on this mindset by listing some examples of computer modeling, such as genetic optimization, and neurocomputing, that he believes GIS should start to utilize more (and are in popular use today).

A part of this piece which leaped out at me was about how people’s sentiments towards computers have changed over time. At one point, a computer’s use was something that must be conserved, and now computers are used everywhere for everything. Everyone assumes that you are connected to the internet all the time; however, this constant connection is also creating new problems concerning digital privacy. I wonder how this constant connection affects GIS data, is it still “non-ideal”, according to Openshaw? This is hard to answer as he never exactly explains how GIS data is “non-ideal” in the paper.

Network Analysis and Topology

Monday, October 21st, 2019

The author introduces the network data structure, the theoretical basis of Network analysis in graph theory and topology. It also discusses that networks are an alternative way of representing the location and the difficulties in the network location problems.
I am particularly interested in the discussion of the 3 types of data models in the evolution of network analysis. The author proposes that it is important to preserve the topological properties of the data whereas these properties also impose difficult constraints on network analysts. The author gave the scenario in which a vertex must exist in the crossing whether or not a true intersection exists, which is problematic when modeling bridges or
tunnels. This reminds me of the project that I’m working on. I plan to use a supervised machining algorithm to extract the road network from satellite images and turn it into a road network. However, the preservation of the topological properties such as the identification of if a crossing is a true intersection or a bridge is extremely difficult. The author then discusses the pure network data structure that is currently widely used in GIS. I think this is a useful topic for me to look into, although I am still not so clear about what is the difference between these two structures and what is planarity requirements that the author mentioned in discussing the two data models.

Thoughts on “Spatial Data Mining Approaches for GIS – A Brief Review”

Monday, October 21st, 2019

This article gives an outline of data formats, data representation, data sources, data mining approaches, related tools, and issue and challenges. The author concluded that “spatial data mining is the analysis of geometric of statistical characteristics and relationships of spatial data”, and it can be used in may fields with different applications.

In terms of spatial data mining tasks, I think other than spatial classification, spatial association rule, spatial clustering, and trend detection, terms like local statistics, spatial autocorrelation, point pattern analysis, etc. should be mentioned or included.

The author also mentioned that the issue and challenges of spatial data mining is data integration and mining huge volume of data. But the author did not explain why this two are challenges. This would be the first things that I felt confused after reading this article.

Then the author provided an architecture of the solution to this two issues and challenges. With no further explanation in detail, I find it really hard to understand why this architecture can solve the above challenges.