Crop area extent estimates and crop type maps provide crucial information for agricultural monitoring and management. Remote sensing imagery in general and, more specifically, high temporal and high spatial resolution data as the ones which will be available with upcoming systems, such as Sentinel-2, constitute a major asset for this kind of application. The goal of this paper is to assess to what extent state-of-the-art supervised classification methods can be applied to high resolution multi-temporal optical imagery to produce accurate crop type maps at the global scale. Five concurrent strategies for automatic crop type map production have been selected and benchmarked using SPOT4 (Take5) and Landsat 8 data over 12 test sites spread all over the globe (four in Europe, four in Africa, two in America and two in Asia). This variety of tests sites allows one to draw conclusions applicable to a wide variety of landscapes and crop systems. The results show that a random forest classifier operating on linearly temporally gap-filled images can achieve overall accuracies above 80% for most sites. Only two sites showed low performances: Madagascar due to the presence of fields smaller than the pixel size and Burkina Faso due to a mix of trees and crops in the fields. The approach is based on supervised machine learning techniques, which need in situ data collection for the training step, but the map production is fully automatic.

Assessment of an Operational System for Crop Type Map Production Using High Temporal and Spatial Resolution Satellite Optical Imagery

Mapping crop phenology using NDVI time-series derived from HJ-1 A/B data

Urbanization is a well-known topic in sustainable development debates as it is known to have great impacts on landscape and environment. Low density, apparently random, scattered or fragmented and leap frogging forms of urban land use, not classified as core urban fabric (town, city, . . . ) nor classified as real ‘countryside’ are studied in this paper. With a thorough literature study of more than 200 publications, a number of interesting conclusions about this important environmental and socio-economical phenomenon can be made. At first, it is generally described as either a type of land use or land use dynamic functioning as ‘divide’ between city and countryside (the urban fringe theory), or it is very often described as the dynamic and fast transformation of rural land into urban land (the sprawl approach). In some cases it forms its own ‘landscape’ and it is called the peri-urban or more correctly semi-urban area. Generally, there seems to be a lack of good definitions and frameworks, although it is studied often and in various scientific disciplines. Prominently, there is an always present dichotomy between rural and urban in all concepts, theories and definitions proposed.

/pdf/semi-urban-areas-in-landscape-research-a-review-3cn5xyault.pdf

Semi-Urban Areas in Landscape Research: A Review

Successful identification and mapping of different cropping patterns under cloudy conditions of a specific crop through remote sensing provides important baseline information for planning and monitoring. In Vietnam, this information is either missing or unavailable; several ongoing projects studying options with radar to avoid earth observation problems caused by the prevailing cloudy conditions have to date produced only partial successes. In this research, optical hyper-temporal Satellite Pour l'Observation de la Terre SPOT VEGETATION SPOT VGT data 1998–2008 were used to describe and map variability in irrigated rice cropping patterns of the Mekong delta. Divergence statistics were used to evaluate signature separabilities of normalized difference vegetation index NDVI classes generated from the iterative self-organizing data analysis technique algorithm ISODATA classification of 10-day SPOT NDVI image series. Based on this evaluation, a map with 77 classes was selected. Out of these 77 mapped classes, 26 classes with prior knowledge that they represent rice were selected to design the sampling scheme for fieldwork and for crop calendar characterization. Using the collected information of 112 farmers’ fields belonging to the 26 selected classes, the map produced provides highly accurate information on rice cropping patterns 94% overall accuracy, 0.93 Kappa coefficient. We found that the spatial distributions of the triple and the double rice cropping systems are highly related to the flooding regime from the Hau and Tien rivers. Areas that are highly vulnerable to flooding in the upper part and those that are saline in the north-western part of the delta mostly have a double rice cropping system, whilst areas in the central and the south-eastern parts mostly have a triple rice cropping system. In turn, the duration of flooding is highly correlated with the decision by farmers to cultivate shorter or longer duration rice varieties. The overall spatial variability mostly coincides with administrative units, indicating that crop pattern choices and water control measures are locally synchronized. Water supply risks, soil acidity and salinity constraints and the anticipated highly fluctuating rice market prices all strongly influence specific farmers’ choices of rice varieties. These choices vary considerably annually, and therefore grown rice varieties are difficult to map. Our study demonstrates the high potential of optical hyper-temporal images, taken on a daily basis, to differentiate and map a high variety of irrigated rice cropping patterns and crop calendars at a high level of accuracy in spite of cloudy conditions.

Mapping the irrigated rice cropping patterns of the Mekong delta, Vietnam, through hyper-temporal SPOT NDVI image analysis

This research investigated three machine learning approaches – decision trees, random forest, and support vector machines – to classify local forest communities at the Huntington Wildlife Forest (HWF), located in the central Adirondack Mountains of New York State, and to identify forest type change over a 20-year period using multi-temporal Landsat satellite Thematic Mapper (TM) data. Because some forest species are sensitive to topographic characteristics, three terrain correction methods – C correction, statistical–empirical (SE) correction, and Variable Empirical Coefficient Algorithm (VECA) – were utilized to account for the topographic effects. Results show that the topographic correction slightly improved the classification accuracy although the improvement was not significant based on the McNemar test. Random forest and support vector machines produced higher classification accuracies than decision trees. Besides, random forest- and support vector machine-based multi-temporal classifications better...

Machine learning approaches for forest classification and change analysis using multi-temporal Landsat TM images over Huntington Wildlife Forest

Sub-pixel classification of SPOT-VEGETATION time series for the assessment of regional crop areas in Belgium

The expansion of urban areas has a negative impact on the environment. The increase of impervious or sealed surfaces is directly proportional to this expansion. The estimation of sealed surfaces has often been executed using remote sensing imagery, although only on a local to regional scale, using medium and recently available high resolution images like LANDSAT TM and IKONOS. In order to develop a global policy and strategy on urban expansion matters, consistent time series of area statistics on urban land use on a national and global level will become indispensable. This research explores the possibilities of SPOT VEGETATION imagery, with a spatial resolution of 1 km, for urban monitoring in order to generate statistics of sealed surfaces over larger zones. While low resolution imagery offers the advantage of covering a large area in small temporal intervals, its spatial resolution is too coarse to monitor most urban objects. In order to tackle this problem, a sub-pixel classification was applied and unmixed sealed surface area statistics were produced. Endmember selection is a key element in the sub-pixel classification process in which the spectrally complex sealed surface class should be distinguished from other general classes. To find the most favourable temporal interval or period for endmember selection, several datasets were developed and explored. SPOT-VEGETATION images were acquired in summer and winter for Flanders (Belgium). This region is characterised by a highly fragmented urban land-cover and large availability of reference data. Spectral unmixing of the multitemporal datasets illustrates that the endmember spectra differs for three different endmember selection techniques, affecting the quality of the final sub-pixel classification. The paper argues that the unmixing result is more sensitive to the endmember selection technique than to the period of image acquisition. It was found that with regard to the tested endmember selection techniques, the Average of Pure Pixels technique gave the best results with an overall accuracy of 81 %, while the combined winter/summer image performed better than the individual summer or winter images.

/pdf/spectral-unmixing-of-low-resolution-images-for-monitoring-maow8xd91n.pdf

Spectral unmixing of low resolution images for monitoring soil sealing


The Global Wind Atlas (GWA) provides high-resolution databases and maps of the wind resource for all land points within 200 km of the coastline, excluding Antarctica. The GWA is used to identify and understand the global, national, regional, and local potential for wind energy and to guide energy specialists, policymakers, and planners in the transition to a sustainable energy system. This information is vital to ensuring the growth of wind energy, helping to transition to a sustainable energy system, which will mitigate climate change and meet the world’s need for reliable, affordable, and clean energy. The GWA uses the established numerical wind atlas methodology to downscale coarse-resolution wind data to microscale, using linearized flow modeling and high-resolution topographic data. There have been three versions of the GWA, each using mesoscale model data at successively higher spatial resolution. A website and Geographic Information System (GIS) files support quick and in-depth analysis. Validation data and analysis, using measurements from tall masts located worldwide, are also provided through the web application. The development process of the GWA involves a dialogue between meteorological modelers, wind energy development experts, web designers, and representatives of the end-users to provide accurate data in a dynamic and relevant way. This article outlines the general method, specific development, and application of the Global Wind Atlas.

https://journals.ametsoc.org/downloadpdf/journals/bams/aop/BAMS-D-21-0075.1/BAMS-D-21-0075.1.pdf

The Global Wind Atlas: A high-resolution dataset of climatologies and associated web-based application

Infrastructure projects are particularly important for the socio-economic development. But roads can also have a large impact on natural environment while opening new tracks. Changes in the accessibility of remote areas could increase illegal activities, in particular the illegal timber logging. Within the Global Monitoring for Environment and Security (GMES) project called G-Mosaic (GMES Services for Management of Operations, Situation Awareness and Intelligence for Regional Crises), the critical asset working group developed geo-spatial information to monitor human and environmental impact of reopening roads, in DRC (Democratic Republic of Congo). This paper presents the Earth Observation (EO) derived tools to monitor forest changes along the route between Kisangani and Bunduki/Bondo. The EO monitoring service combines frequently large area monitoring at high resolution (20 - 30 m) with detailed annual monitoring at very high resolution (0.5 m). First results quantify the number of clear-cuts along the road in the Rubi-Tele reserve. The number of patches increase from 2010 to 2011 but the total area in these clear-cuts is constant during the period. The potential application of the developed tools in the context of REDD will be further developed in the REDDiness project. The project was obtained in the last calls of the 7 th European Commission (EC) Framework Programme and has just started in 2011. In REDDiness, up-to-date Earth Observation (EO) techniques will be adapted to local situation in order to assist Central African countries in addressing the challenges of Reducing Emissions from Deforestation and forest Degradation (REDD). For both G-Mosaic and REDDiness projects, there is a high interest of measuring and mapping changes in the world‟s humid tropical forests to derive national and regional figures for multilateral agreements and sustainable forest management.

Ides Bauwens

Papers

Sub-pixel classification of SPOT-VEGETATION time series for the assessment of regional crop areas in Belgium

Spectral unmixing of low resolution images for monitoring soil sealing

The Global Wind Atlas: A high-resolution dataset of climatologies and associated web-based application

Monitoring the reopening of roads in the democratic republic of congo with earth observation data