Preprints (not yet peer-reviewed)

11 downloads
97 views

The NIST DSE Plant Identification challenge is a new periodic competition focused on improving and generalizing remote sensing processing methods for forest landscapes. To compete in the competition, I created a pipeline to perform three remote sensing tasks. First,...

["Biogeography","Ecology","Natural Resource Management","Forestry","Spatial and Geographic Information Science"]
doi:10.7287/peerj.preprints.26977v1
64 downloads
119 views

To accelerate scientific progress on remote tree classification—as well as biodiversity and ecology sampling—The National Institute of Science and Technology created a community-based competition where scientists were invited to contribute informatics methods for...

["Ecology","Data Mining and Machine Learning","Data Science","Forestry","Spatial and Geographic Information Science"]
doi:10.7287/peerj.preprints.26971v1
39 downloads
124 views

Background. Biogeographers assess how species distributions and abundances affect the structure, function, and composition of ecosystems. Yet we face a major challenge: it is difficult to precisely map species across landscapes. Novel Earth observations could obviate...

["Biogeography","Ecology","Data Mining and Machine Learning","Spatial and Geographic Information Science"]
doi:10.7287/peerj.preprints.26972v1
39 downloads
90 views

This paper describes the methods used in the submission for team Shawn for the data science competition “Airborne Remote Sensing to Ecological Information”. I used canopy height rasters as well as NDVI rasters of the study area. I first filtered out pixels using...

["Ecology","Forestry","Spatial and Geographic Information Science"]
doi:10.7287/peerj.preprints.26967v1
237 downloads
494 views

Ecology has reached the point where data science competitions, in which multiple groups solve the same problem using the same data by different methods, will be productive for advancing quantitative methods for tasks such as species identification from remote sensing...

["Ecology","Data Mining and Machine Learning","Data Science","Forestry","Spatial and Geographic Information Science"]
doi:10.7287/peerj.preprints.26966v1
78 downloads
122 views

Climate change has profoundly impacted tropical ecosystems, critical for sustaining economies and community livelihoods at local to global scales. Rapid population growth has further negatively impacted natural resource management and upsetting the socio-ecological...

["Agricultural Science","Ecology","Climate Change Biology","Natural Resource Management","Spatial and Geographic Information Science"]
doi:10.7287/peerj.preprints.26963v2
641 downloads
894 views

Random forest and similar Machine Learning techniques are already used to generate spatial predictions, but spatial location of points (geography) is often ignored in the modeling process. Spatial auto-correlation, especially if still existent in the cross-validation...

["Biogeography","Soil Science","Computational Science","Data Mining and Machine Learning","Spatial and Geographic Information Science"]
doi:10.7287/peerj.preprints.26693v2
59 downloads
159 views

Knowledge of deep-sea species and their ecosystems is limited due to the inaccessibility of the areas and the prohibitive cost of conducting large-scale field studies. My graduate research has used predictive modeling methods to map hexactinellid sponge habitat...

["Biodiversity","Ecology","Marine Biology","Spatial and Geographic Information Science","Biological Oceanography"]
doi:10.7287/peerj.preprints.26815v1
395 downloads
707 views

Potential Natural Vegetation (PNV) is the vegetation cover in equilibrium with climate, that would exist at a given location non-impacted by human activities. PNV is useful for raising public awareness about land degradation and for estimating land potential. This...

["Biogeography","Computational Biology","Plant Science","Data Mining and Machine Learning","Spatial and Geographic Information Science"]
doi:10.7287/peerj.preprints.26811v1
58 downloads
144 views

Here we demonstrate how to globally detect regions of high plankton diversity (the lower levels of the trophic chain) and also higher level consumers' diversity using satellite information of 'fluid dynamical niches' characterized by spatially and temporally different...

["Biodiversity","Biogeography","Marine Biology","Spatial and Geographic Information Science","Biological Oceanography"]
doi:10.7287/peerj.preprints.26795v1
62 downloads
148 views

As an island nation, the UK is surrounded by water, spanning from the coast and intertidal, to the circalittoral and deep-sea. Understanding the changing condition and resilience of marine biodiversity within these vastly different water masses is of key importance...

["Biodiversity","Ecology","Marine Biology","Environmental Impacts","Spatial and Geographic Information Science"]
doi:10.7287/peerj.preprints.26784v1
70 downloads
158 views

A core objective of marine protected areas (MPA) is to conserve regions of high biodiversity. Establishing biodiversity baselines – e.g. local species richness and community structure – is necessary to monitor change within MPAs, but such knowledge is often lacking...

["Biodiversity","Biogeography","Conservation Biology","Marine Biology","Spatial and Geographic Information Science"]
doi:10.7287/peerj.preprints.26748v1
319 downloads
691 views

The demand for reproducibility of research is on the rise in disciplines concerned with data analysis and computational methods. In this work existing recommendations for reproducible research are reviewed and translated into criteria for assessing reproducibility...

["Science Policy","Computational Science","Data Science","Spatial and Geographic Information Science"]
doi:10.7287/peerj.preprints.26561v1
95 downloads
148 views

Background. The consequences of past or future climate change have been studied in many physical and biological systems, and their effects could change the ecology and spatial distribution of suitable areas for a wide variety of organisms. Methods. We analyzed...

["Biogeography","Zoology","Climate Change Biology","Spatial and Geographic Information Science"]
doi:10.7287/peerj.preprints.26560v1
140 downloads
86 views

Despite the large amount of accessible spatial information, the issue of estimating aboveground biomass through remote sensing, especially radar, remains a challenge in complex ecosystems such as tropical forests. One of the advantages of radar sensors is that...

["Ecology","Spatial and Geographic Information Science"]
doi:10.7287/peerj.preprints.26534v1
What is a PeerJ Preprint?

A PeerJ Preprint is a draft of an article, abstract, or poster that has not yet been peer-reviewed for formal publication. Submit a draft, incomplete, or final version of your work for free.

Submissions today can be approved by Editorial Staff and online in 24 hours.

Establish precedent. Solicit feedback. Publish updates.

Refine by manuscript type

Top subject areas - Preprints

Top subject areas - People

View all subject areas