A contribution towards simplifying area-wide tsetse surveys using medium resolution meteorological satellite data

2001 ◽  
Vol 91 (5) ◽  
pp. 333-346 ◽  
Author(s):  
G. Hendrickx ◽  
A. Napala ◽  
J.H.W. Slingenbergh ◽  
R. De Deken ◽  
D.J. Rogers
Keyword(s):  
Satellite Imagery ◽  
Satellite Data ◽  
Field Data ◽  
Spatial Epidemiology ◽  
Remotely Sensed ◽  
Optimal Number ◽  
Tsetse Fly ◽  
Training Data ◽  
Remotely Sensed Data ◽  
Distribution Limits

AbstractA raster or grid-based Geographic Information System with data on tsetse, trypanosomiasis, animal production, agriculture and land use has recently been developed in Togo. The area-wide sampling of tsetse fly, aided by satellite imagery, is the subject of two separate papers. This paper on a first paper, published in this journal, describing the generation of digital tsetse distribution and abundance maps and how these accord with the local climatic and agro-ecological setting. Such maps when combined with data on the disease, the hosts and their owners, should contribute the knowledge of the spatial epidemiology of trypanosomiasis and assist planning of integrated control operations. Here we address the problem of generating tsetse distribution and abundance maps from remotely sensed data, using a restricted amount of field data. Different discriminant models have been applied using contemporary tsetse data and remotely sensed, low resolution data acquired from the National Oceanographic and Atmospheric Administration (NOAA) and Meteosat platforms. The results confirm the potential of satellite data application and multivariate for the prediction of the tsetse distribution and abundance. This opens up new avenues because satellite predictions and field data may be combined to strengthen and/or substitute one another. The analysis shows how the strategic incorporation of satellite imagery may minimize field of data. Field surveys may be modified and conducted in two stages, first concentrating on the expected fly distribution limits and thereafter on fly abundance. The study also shows that when applying satellite data, care should be taken in selecting the optimal number of predictor because this number varies with the amount of training data for predicting abundance and on the homogeneity of the distribution limits for predicting fly presence. Finally, it is suggested that in addition to the use of contemporary training data and predictor variables, training predicted data sets should refer to the same eco-geographic zone.

scholarly journals Multilayer Soil Moisture Mapping at a Regional Scale from Multisource Data via a Machine Learning Method

2019 ◽  
Vol 11 (3) ◽  
pp. 284 ◽  
Author(s):  
Linglin Zeng ◽  
Shun Hu ◽  
Daxiang Xiang ◽  
Xiang Zhang ◽  
Deren Li ◽  
...  
Keyword(s):  
Machine Learning ◽  
Soil Moisture ◽  
Regional Scale ◽  
Remotely Sensed ◽  
Temporal Variations ◽  
Training Data ◽  
Estimation Accuracy ◽  
Learning Approaches ◽  
Remotely Sensed Data ◽  
Deep Soil

Soil moisture mapping at a regional scale is commonplace since these data are required in many applications, such as hydrological and agricultural analyses. The use of remotely sensed data for the estimation of deep soil moisture at a regional scale has received far less emphasis. The objective of this study was to map the 500-m, 8-day average and daily soil moisture at different soil depths in Oklahoma from remotely sensed and ground-measured data using the random forest (RF) method, which is one of the machine-learning approaches. In order to investigate the estimation accuracy of the RF method at both a spatial and a temporal scale, two independent soil moisture estimation experiments were conducted using data from 2010 to 2014: a year-to-year experiment (with a root mean square error (RMSE) ranging from 0.038 to 0.050 m3/m3) and a station-to-station experiment (with an RMSE ranging from 0.044 to 0.057 m3/m3). Then, the data requirements, importance factors, and spatial and temporal variations in estimation accuracy were discussed based on the results using the training data selected by iterated random sampling. The highly accurate estimations of both the surface and the deep soil moisture for the study area reveal the potential of RF methods when mapping soil moisture at a regional scale, especially when considering the high heterogeneity of land-cover types and topography in the study area.

scholarly journals Effects of Training Set Size on Supervised Machine-Learning Land-Cover Classification of Large-Area High-Resolution Remotely Sensed Data

2021 ◽  
Vol 13 (3) ◽  
pp. 368
Author(s):  
Christopher A. Ramezan ◽  
Timothy A. Warner ◽  
Aaron E. Maxwell ◽  
Bradley S. Price
Keyword(s):  
Machine Learning ◽  
Sample Size ◽  
Remotely Sensed ◽  
Training Data ◽  
Supervised Machine Learning ◽  
Sample Sizes ◽  
Remotely Sensed Data ◽  
Large Area ◽  
Training Set ◽  
Set Size

The size of the training data set is a major determinant of classification accuracy. Nevertheless, the collection of a large training data set for supervised classifiers can be a challenge, especially for studies covering a large area, which may be typical of many real-world applied projects. This work investigates how variations in training set size, ranging from a large sample size (n = 10,000) to a very small sample size (n = 40), affect the performance of six supervised machine-learning algorithms applied to classify large-area high-spatial-resolution (HR) (1–5 m) remotely sensed data within the context of a geographic object-based image analysis (GEOBIA) approach. GEOBIA, in which adjacent similar pixels are grouped into image-objects that form the unit of the classification, offers the potential benefit of allowing multiple additional variables, such as measures of object geometry and texture, thus increasing the dimensionality of the classification input data. The six supervised machine-learning algorithms are support vector machines (SVM), random forests (RF), k-nearest neighbors (k-NN), single-layer perceptron neural networks (NEU), learning vector quantization (LVQ), and gradient-boosted trees (GBM). RF, the algorithm with the highest overall accuracy, was notable for its negligible decrease in overall accuracy, 1.0%, when training sample size decreased from 10,000 to 315 samples. GBM provided similar overall accuracy to RF; however, the algorithm was very expensive in terms of training time and computational resources, especially with large training sets. In contrast to RF and GBM, NEU, and SVM were particularly sensitive to decreasing sample size, with NEU classifications generally producing overall accuracies that were on average slightly higher than SVM classifications for larger sample sizes, but lower than SVM for the smallest sample sizes. NEU however required a longer processing time. The k-NN classifier saw less of a drop in overall accuracy than NEU and SVM as training set size decreased; however, the overall accuracies of k-NN were typically less than RF, NEU, and SVM classifiers. LVQ generally had the lowest overall accuracy of all six methods, but was relatively insensitive to sample size, down to the smallest sample sizes. Overall, due to its relatively high accuracy with small training sample sets, and minimal variations in overall accuracy between very large and small sample sets, as well as relatively short processing time, RF was a good classifier for large-area land-cover classifications of HR remotely sensed data, especially when training data are scarce. However, as performance of different supervised classifiers varies in response to training set size, investigating multiple classification algorithms is recommended to achieve optimal accuracy for a project.

Grazing Gradients in Central Australian Rangelands: Ground Verification of Remote Sensing-Based Approaches.

1993 ◽  
Vol 15 (2) ◽  
pp. 217 ◽  
Author(s):  
GN Bastin ◽  
AD Sparrow ◽  
G Pearce
Keyword(s):  
Satellite Data ◽  
Vegetation Cover ◽  
Field Data ◽  
Graphical Representation ◽  
Woody Species ◽  
Soil Surface ◽  
Grazing Pressure ◽  
Remotely Sensed Data ◽  
Suitable Technique ◽  
Grazing Behaviour

Remotely-sensed data collected by satellites have been proposed for investigating grazing effects across the large paddocks of arid Australia. These data are used to compute indices of vegetation cover which are then analysed with reference to patterns of grazing behaviour around watering points. Grazing pressure typically increases as water is approached, resulting in a decrease in herbage cover. This pattern of cover change is called a grazing gradient. The change in these gradients from a dry to wet period forms the basis for assessing land degradation as described in an accompanying paper. This study demonstrates that grazing gradients do exist, that they can be detected with field-based methods of data collection, and that there is close correspondence between ground data and indices of vegetation cover obtained from contemporary Landsat Multispectral Scanner satellite data. Field data representing aerial cover of the herbage and woody species layers were collected along transects radiating away from water at two sites grazed by cattle in central Australia. Graphical representation of the litter and herbage components demonstrate that gradients of decreasing cover attributable to increasing grazing pressure occur along all, or sections, of each transect. Highly significant correlations exist between the field data and satellite indices of vegetation cover. Localised shrub increase and patches of recent erosion obscured trends of increasing cover with distance from water on parts of some transects. Soil surface state (describing past erosion) was a significant covariate of cover change at one site. Our ability to characterise gradients of increasing vegetation cover with distance from water using both field and satellite data should mean that the grazing gradient method, when used with satellite data, is a suitable technique for assessing the extent of landscape recovery following good rainfall.

Remotely Sensed Wind, Wave, and Sea Level for European Sea Climatology

2002 ◽  
Author(s):  
Abderrahim Bentamy ◽  
Hafedh Hajji ◽  
Carlos Guedes Soares
Keyword(s):  
Sea Level ◽  
Satellite Data ◽  
Wind Wave ◽  
Remotely Sensed ◽  
Wind Data ◽  
Remotely Sensed Data ◽  
Level Data ◽  
Wind Sea ◽  
Initial Results ◽  
And Sea Level

This paper provides an overview of the analysis of remotely sensed data that has been performed within the scope of a project aiming at obtaining a 40-year hindcast of wind, sea level and wave climatology for the European waters. The satellite data, including wind, wave and sea-level data, are collected for the same areas and are calibrated with available and validated measurements. It will be used to be compared with the hindcast results, so as to yield some uncertainty measures related to the data. This paper describes the type of data that will be used and presents the initial results, which concern mainly remote sensed wind data.

scholarly journals Variational assimilation of remotely sensed flood extents using a 2-D flood model

2014 ◽  
Vol 18 (11) ◽  
pp. 4325-4339 ◽  
Author(s):  
X. Lai ◽  
Q. Liang ◽  
H. Yesou ◽  
S. Daillet
Keyword(s):  
Data Assimilation ◽  
Cost Function ◽  
Satellite Imagery ◽  
Numerical Experiments ◽  
Remotely Sensed ◽  
Flood Routing ◽  
Remotely Sensed Data ◽  
Variational Assimilation ◽  
Flood Model ◽  
The Rich

Abstract. A variational data assimilation (4D-Var) method is proposed to directly assimilate flood extents into a 2-D dynamic flood model to explore a novel way of utilizing the rich source of remotely sensed data available from satellite imagery for better analyzing or predicting flood routing processes. For this purpose, a new cost function is specially defined to effectively fuse the hydraulic information that is implicitly indicated in flood extents. The potential of using remotely sensed flood extents for improving the analysis of flood routing processes is demonstrated by applying the present new data assimilation approach to both idealized and realistic numerical experiments.

Advance in Monitoring Forest Fire in China Based on Multi-Satellite Data

2012 ◽  
Vol 518-523 ◽  
pp. 5668-5672 ◽  
Author(s):  
Jia Hua Zhang ◽  
Feng Mei Yao
Keyword(s):  
Forest Fire ◽  
Satellite Data ◽  
Hot Spots ◽  
Remotely Sensed ◽  
Remotely Sensed Data ◽  
Burned Areas ◽  
Noaa Avhrr

The advance in monitoring forest fire in China based on multi-Satellite data were discussed in the paper. Since the 1980s in China, the satellite remotely-sensed data have been acquired, such as NOAA/AVHRR, FY-series, MODIS, CBERS, and ENVISAT, have been widely utilized for monitoring forest fire hot spots and burned areas in China. Some developed algorithms have been utilized for detecting the forest fire hot spots.

scholarly journals Variational assimilation of remotely sensed flood extents using a two-dimensional flood model

2013 ◽  
Vol 10 (8) ◽  
pp. 11185-11220
Author(s):  
X. Lai ◽  
Q. Liang ◽  
H. Yesou
Keyword(s):  
Data Assimilation ◽  
Satellite Imagery ◽  
Numerical Experiments ◽  
Remotely Sensed ◽  
Flood Routing ◽  
Two Dimensional ◽  
Remotely Sensed Data ◽  
Variational Assimilation ◽  
Flood Model ◽  
The Rich

Abstract. A variational data assimilation (4D-Var) method is proposed to directly assimilate flood extents into a two-dimensional (2-D) dynamic flood model, to explore a novel way of utilizing the rich source of remotely sensed data available from satellite imagery for better analyzing or predicting flood routing processes. For this purpose, a new cost function is specially defined to effectively fuse the hydraulic information that is implicitly indicated in flood extents. The potential of using remotely-sensed flood extents for improving the analysis of flood routing processes is demonstrated by applying the present new data assimilation approach to both idealized and realistic numerical experiments.

Sign in / Sign up

Export Citation Format

Share Document