Small-scale Maps Research Articles

Forest vegetation mapping in the North of the Koryak Region

The distribution boundaries of light-coniferous and deciduous forests formed by larch (Larix cajanderi Mayr), stone-birch (Betula ermanii Cham.), white birch (Betula platyphylla Sukacz.), poplar (Populus suaveolens Fisch.), chosenia (Chosenia arbutifolia (Pall.) A Skvorts.), alder (Alnus hirsute (Spach) Turcz. ex Rupr.) and willow trees (Salix udensis Trautv. et C.A. Mey., S. schwerinii E.L. Wolf), as well as elfin wood communities formed by Siberian dwarf-pine (Pinus pumila (Pall.) Rgl.), dwarf-alder (Alnus fruticosa Rupr.), and dwarf-birch (Betula middendorffii) have been clarified for the North of the Koryak Region. The remote sensing data, aerial photographs, original relevés and itinerary research data were used for small-scale forest vegetation mapping. A map of forests and elfin woods allocation in the mainland part of the Koryak Region was compiled. With the help of this map, the boundaries of the new geobotanical subdivision of the North of Koryak Region will be clarified and the most important phytogeographical boundaries within the Beringian forest-tundra zone will be determined.

STEREO GRAPHIC PROJECTION AND ITS APPLICATIONS

In this paper, we introduce stereographic projection and its applications. In today’s time, this is one of the most widely used stereo projections. This projection is used in polar areas and also used in small-scale maps. This is a very useful tool to solving the orientation problems in structural geology, mathematics, and also in the studying of crystal structures and helpful to deduce how those structures relate to planes with crystal.

Leveraging Deep Neural Networks to Map Caribou Lichen in High-Resolution Satellite Images Based on a Small-Scale, Noisy UAV-Derived Map

Lichen is an important food source for caribou in Canada. Lichen mapping using remote sensing (RS) images could be a challenging task, however, as lichens generally appear in unevenly distributed, small patches, and could resemble surficial features. Moreover, collecting lichen labeled data (reference data) is expensive, which restricts the application of many robust supervised classification models that generally demand a large quantity of labeled data. The goal of this study was to investigate the potential of using a very-high-spatial resolution (1-cm) lichen map of a small sample site (e.g., generated based on a single UAV scene and using field data) to train a subsequent classifier to map caribou lichen over a much larger area (~0.04 km2 vs. ~195 km2) and a lower spatial resolution image (in this case, a 50-cm WorldView-2 image). The limited labeled data from the sample site were also partially noisy due to spatial and temporal mismatching issues. For this, we deployed a recently proposed Teacher-Student semi-supervised learning (SSL) approach (based on U-Net and U-Net++ networks) involving unlabeled data to assist with improving the model performance. Our experiments showed that it was possible to scale-up the UAV-derived lichen map to the WorldView-2 scale with reasonable accuracy (overall accuracy of 85.28% and F1-socre of 84.38%) without collecting any samples directly in the WorldView-2 scene. We also found that our noisy labels were partially beneficial to the SSL robustness because they improved the false positive rate compared to the use of a cleaner training set directly collected within the same area in the WorldView-2 image. As a result, this research opens new insights into how current very high-resolution, small-scale caribou lichen maps can be used for generating more accurate large-scale caribou lichen maps from high-resolution satellite imagery.

BRITISH MILITARY CONTRIBUTIONS TO THE GEOLOGY OF MALTA, PART 1: NINETEENTH CENTURY FOUNDATIONS

Malta, an island in the central Mediterranean Sea, was fortified as a base for the Knights Hospitaller 1530–1798 and to provide major harbours for the British Royal Navy after 1813. Men with British military associations (all subsequently to attain some distinction in public and/or academic life) were amongst the many pioneers of Maltese geology who established the essence of its outcrop stratigraphy and structure: a circa 300-metre-thick sequence of near-horizontal mid-Cenozoic fossiliferous limestones punctuated by a ‘blue clay/marl’, cut by a series of major faults and penetrated by several caves and fissures whose infill contained significant remains of Pleistocene vertebrates. Between 1843 and 1856, Lieutenant (later Vice-Admiral) Thomas Abel Brimage Spratt (1811–1888) defined major units in the bedrock sequence, Colonel (later Major-General) Sir William Reid (1791–1858) promoted publication of a geological memoir, and a 1:31,680-scale geological map prepared by the 3rd Earl of Ducie on a Royal Engineers topographical base map was published under Royal Engineer auspices. Mostly between 1860 and 1866, Captain (later Professor) Frederick Wollaston Hutton (1836–1905) and Surgeon (later Deputy Surgeon-General and Professor) Andrew Leith Adams (1827–1882) made field observations that refined earlier interpretations of stratigraphy and structure and generated revised but small-scale maps. They also collected specimens that facilitated specialist identifications of Malta’s fossil faunas, including foraminifera by Thomas Rupert Jones (1819–1911), Professor of Geology at the Royal Military College, Sandhurst. Rock specimens were sent in 1888 by Surgeon-Captain David (later Surgeon-General Sir David) Bruce (1855–1931) and the former engineer Lieutenant (and later Professor) Osbert Chadwick (1844–1913) to the pioneer oceanographer John (later Sir John) Murray (1841–1914). They stimulated Murray’s benchmark study 1889–1890 of Malta’s sedimentary sequence and fossil foraminifera, and their palaeoenvironmental interpretation, plus his compilation of a 1:129,254-scale geological map. These prompted extensive local studies and collection of macrofossil specimens by schoolmaster (later Lieutenant-Colonel) John Henry Cooke (1862–1933). By the end of the century, representative Maltese fossils had been presented for specialist study and identification or description to major museums in England, Scotland and Italy, facilitating improved correlation of Maltese strata with Oligo-Miocene successions elsewhere.

Assessing food availability: A novel approach for the quantitative estimation of the contribution of small farms in regional food systems in Europe

Recent findings on the contribution of smallholders to global food production and security challenge the values used in several reports of international organizations. The skewed distribution of the number of farms and the agricultural area by farm size may explain overestimations in small farms' food production. In fact, the highest values found in literature seem to be more strongly correlated to the total number of small farms than to the actual area they cover, suggesting errors in the estimation procedures. Additionally, a significant part of the small farms is not considered in official statistics, thus limiting the use of the data and also leading to underestimations. New efforts are thus needed to develop and apply methodologies to reduce the error and uncertainty of these estimates. In this paper we demonstrate the progress obtained by using a novel approach to provide new and more accurate estimates on the availability of food produced in small farms in 17 European regions (NUTS-3 level) distributed in 8 countries. Our assessment was carried out using two data sets: [1] data on crop area and production for a priori selected key products in each reference region, collected through questionnaires to small producers; [2] remote sensing-based products derived from Sentinel-1 and Sentinel-2 images, including crop type maps with ground-truth validation and small-scale farming systems probability maps. To reduce error propagation resulting from self-reported yield estimates, we used robust measures of central tendency based on Tukey's bi-weight function to compute the overall production in small farms in each region, minimizing the effect of outliers. The self-reported yields by small farmers were also compared with national and regional values of productivity per unit area and discussed in light of previous findings. Our results highlight not only the importance of small farms in the European context, but also their diversity in productivity levels. In addition to the novel methodological steps that underlie our study, which involve the combination of remote sensing data with data resulting from field surveys, the approach undertaken allows to better understand the contribution of small farmers to food security in each regional context, and the potential they have to support short food supply chains. Our findings can be key in supporting policy options that aim to enhance food security by reducing the EU footprint through strengthening and diversifying regional food systems.

The Benefits of Combining Global and Local Data—A Showcase for Valuation and Mapping of Mangrove Climate Regulation and Food Provisioning Services within a Protected Area in Pará, North Brazil

Mangrove forests provide a large variety of ecosystem services (ES) to coastal societies. Using a case study focusing on the Ajuruteua peninsula in Northern Brazil and two ES, food provisioning (ES1) and global climate regulation (ES2), this paper proposes a new framework for quantifying and valuing mangrove ES and allow for their small-scale mapping. We modelled and spatialised the two ES from different perspectives, the demand (ES1) and the supply (ES2) side respectively. This was performed by combining worldwide databases related to the global human population (ES1) or mangrove distribution and canopy height (ES2) with locally derived parameters, such as crab catches (ES1) or species-specific allometric equations based on local estimates of tree structural parameters (ES2). Based on this approach, we could estimate that the area delivers the basic nutrition of about 1400 households, which equals 2.7 million USD, and that the mangrove biomass in the area contains 2.1 million Mg C, amounting to 50.9 million USD, if it were paid as certificates. In addition to those figures, we provide high-resolution maps showing which areas are more valuable for the two respective ES, information that could help inform management strategies in the future.

The MinimumBreak algorithm applied to a series of road turns

Cartographic generalization is the process of small-scale map production from large-scale maps. When the size of the map is reduced, the objects present in the latter can conflict with each other. There may be overlapping of objects, coalesced roads, or imperceptibility problems. Generalization solves these problems through algorithms. However, the generalization is not yet automated due to the lack of algorithms. In this article, a new algorithm for processing turn series on a road to correct the coalescence is investigated. Tests as well as comparisons with existing algorithms are going to be conducted. This research has proven to be beneficial to the field of cartography as there is a lack of algorithms treating complex series of turns when producing a map. The samples used for the study are winding mountainous roads from Algeria, China, Norway, Switzerland, and France.

Информационно-картографическое обеспечение исследования потенциальных трансформаций геосистем для цифрового атласа «Байкальский регион: общество и природа»

Based on the electronic atlas “Baikal Region: Society and Nature”, the problem of landscape-cartographic support for studying the transformations of vast territories is being solved. The transformation of geosystems is understood as changes in the natural environment due to spontaneous development or anthropogenic interference. In this context, potential and actual transformations are distinguished. The research of potential transformations is associated with a geographic forecast of possible changes in the state of the environment due to external impact, and current transformations include an assessment of its current ecological state. The area under investigation includes the territory of the Baikal basin, and the northern regions of Mongolia. This aspect is realized through the integration of a multitude of geographical data on the structure of natural systems, their sustainability and trends of anthropogenic transformations into a single target cartographic information system (CIS). The main requirement for the content of the target block of maps is the reliability of the results of a comprehensive research and their evidentiality if used to make management decisions to optimize the environment. A logical and methodological coherence of small-scale target mapping of the natural environment of a vast territory has been developed. The analysis of natural structures was carried out and a basic inventory map of geosystems of scale (M 1:5,000,000) was created. We developed a set of geosystem characteristics and carried out an environmental interpretation of information and integrated environmental mapping, aside from that implemented geoecological zoning of the territory. Based on the information synthesis of the obtained data and knowledge about the modern landscape structure of the region, the methods of polysystem analysis, we revealed the nature of sustainability, functions, value characteristics of geosystems and the patterns of their anthropogenic transformations. The presence of a single set of maps will provide a study of questions about potential and relevant transformations of geosystems. The small-scale maps of the Baikal region, compiled in a certain sequence on the basis of a single structural-hierarchical specialized classification, reflect a complex of environmental conditions that are important for making constructive-geographical, design, managerial, and environmental decisions.

Применение ГИС-технологий в зоогеографическом картографировании (на примере Пермского края и города Перми)

Nowadays there is a lot of information about species composition, distribution and abundance of terrestrial vertebrates in the Perm Territory in different literature and departmental papers. Consolidation of data by creating the theme geodatabase and zoogeographical maps helps not only imagine the structure and distribution of vertebrates on the territory but also identify the main patterns of their habitat. There are some principles of designing and creating zoogeographical maps of the Perm Territory and Perm City which aim is to realize the two projects. They are considered in the article. The first project is the creation of zoogeographical chapter in the integrated geographical atlas of the Perm Territory; the second—is cartographic support for birding in Perm. The two projects are united by one theme of the given research. The thematic content of the maps is based on the scientific vertebrate system. All the 15 maps in the zoogeographical chapter are designed in such a way that they contain various maps on the given theme. There examined the principles of designing small-scale zoogeographical educational maps for different age groups (primary, secondary and higher education). Map-booklet “Birding in Perm” in scale 1:65,000 is designed for birdwatchers-beginners with no age limits. All maps are in ArcGIS 10.4.1. The improvement in methodology of creating zoogeographical maps and legends by implementation geoinformational technologies and computer processing expands the modern opportunities for thematic zoogeographical cartography.

Wide-Area Land Cover Mapping With Sentinel-1 Imagery Using Deep Learning Semantic Segmentation Models

Land cover (LC) mapping is essential for monitoring the environment and understanding the effects of human activities on it. Recent studies demonstrated successful applications of specific deep learning models to small-scale LC mapping tasks (e.g., wetland mapping). However, it is not readily clear which of the existing state-of-the-art models for natural images are the best candidates to be taken for the particular remote sensing task and data. In this article, we answer that question for mapping the fundamental LC classes using the satellite imaging radar data. We took ESA Sentinel-1 C-band SAR images acquired during the whole summer season of 2018 in Finland, which are representative of the land cover in the country. CORINE LC map was used as a reference, and the models were trained to distinguish between the five major CORINE-based classes. We selected seven among the state-of-the-art semantic segmentation models so that they cover a diverse set of approaches: U-Net, DeepLabV3+, PSPNet, BiSeNet, SegNet, FC-DenseNet, and FRRN-B, and further fine-tuned them. Upon evaluation and benchmarking, all the models demonstrated solid performance with overall accuracy between 87.9% and 93.1%, with good to a very good agreement (Kappa statistic between 0.75 and 0.86). The two best models were fully convolutional DenseNets (FC-DenseNet) and SegNet (encoder-decoder-skip), with the latter having a much shorter inference time. Overall, our results indicate that the semantic segmentation models are suitable for efficient wide-area mapping using satellite SAR imagery and provide baseline accuracy against which the newly proposed models should be evaluated.

Наследие Н. И. Кузнецова в картографировании растительности (к 100-летию Отдела геоботаники Ботанического института им. В. Л. Комарова)

The development of vegetation mapping as a research branch in geobotany and botanical geography is connected with the history of the Geobotany Department of the Komarov Botanical Institute. The 100th anniversary of the Department will be celebrated in 2022. Nikolai Ivanovich Kuznetsov — a world-renowned scientist, who had great scientific and organizational experience — was assigned to lead the new department in 1922. In connection with the requests of the practice, the main task of the Department of Geobotany was the development of geobotanical cartography. Despite the difficult period for the country, research in this field of geobotany started. N. I. Kuznetsov wrote an extensive program of works on vegetation mapping, which he presented already in 1923 at the First All-Union Gosplan [Government plan] Conference on the Study of the Productive Forces of Nature. N. I. Kuznetsov put forward an idea to create four types of maps reflected the complex phenomena of geographical distribution of vegetation. One of these maps is a geobotanical map, which shows the main types of vegetation cover of the country. An important stage of analytical work in botanical geography and cartography is producing a floristic map that shows the boundaries of the main woody, shrubby and herbaceous plants. The distribution of modern types of plant communities should contain a historical map. A map of geobotanical regionalization (zoning) should represent the synthesis of both maps (Kuznetsov, 1924). N. I. Kuznetsov considered vegetation mapping as a process consisting of several stages: creating detailed maps should be preceded by the making of small-scale survey maps. He compiled the “Vegetation map of the European part of the USSR” in 1 : 4 000 000 scale (Kuznetsov, 1928c), which contained 46 mapped units of zonal and non-zonal plant communities. This map legend was the first one based on the regional-typological approach. The second stage of the work — the compilation of medium-scale (1 : 1 050 000, and then 1 : 1 000 000) maps of the European part of the USSR was also carried out. According to Kuznetsov’s original plan, the map was supposed to consist of 18 sheets. During Kuznetsov’s lifetime, 8 sheets were published (5, 6, 7, 9, 10, 14, 15, 16). They covered the Middle and Lower Volga Region, the Northern Caspian Sea, the forest-steppe and steppe south of the European part of the USSR, the Crimea, as well as the north of the Kola Peninsula and the Vologda Region (Geobotanicheskaya …, 1927–1932). In addition to the sheet 14 titled “Geobotanical map of the European part of the USSR” (Fig. 1а, б) N. I. Kuznetsov and co-authors compiled the “Botanical-geographic map of the European part of the USSR” (Fig. 2а, б). These maps summed up the data available in the 1930s on the vegetation of the European part of the USSR, and this was their great scientific value. Although they were not very detailed, they had an economic significance. The principles, theoretical concepts and design of these maps were innovative. The principles of vegetation mapping developed by N. I. Kuznetsov have become traditional for the Russian school. These are following: map legends based on the regional-typological principle, maps show modern vegetation as well as restored one as a background, maps reflect the interrelationships of vegetation with the main environmental factors, usage of floristic features of the mapped territory. Kuznetsov’s ideas formed some general theoretical foundations that became characteristic of the Russian botanical-cartographic school.

"Jissoku-Yochizu" which should be newly found manuscripts as the small scale map of Japan originally surveyed by INOH Tadataka in 1821

"Jissoku-Yochizu" which should be newly found manuscripts as the small scale map of Japan originally surveyed by INOH Tadataka in 1821

Metodyka wyznaczania godła mapy w układzie International Map of the World (IMW).

The systematic division into section sheets adopted in the International World Map is the standard in many countries. This division is used for most types of small-scale maps. Due to the scope of application, it is also often the basis for indexing orthophoto images and data from laser scanning. Data accummulated in central State resources cover entire countries. Their coverage includes more than information obtained and processed for the users’ needs in the source format. Increasingly often, data is transformed into formats that facilitate their application (e.g. setting up a GRID for a digital terrain model). The need for quick spatial identification is a determinant of the availability of resources stored in these databases. The dynamic development of Open Source software in the fields of GIS is another increasingly broad area of study, and the research focus of scientists from around the world. They see it not only as a ready-made tool for conducting spatial analyses, but also in terms of searching for algorithmic solutions to meet the needs resulting from the requirement to process ever larger amounts of this type of data. The present paper discusses the method for designating a map sheet identification number (index) in a selected scale, based on the longitude and latitude of the given point. An unquestionable advantage of the presented solution is the possibility of dividing map sheets into scales, which were missing in their basic description. It follows from the fact that this spatial indexing method is indispensable for large amounts of data.

Finding Optimal Sequences for Area Aggregation—A ⋆ vs. Integer Linear Programming

To provide users with maps of different scales and to allow them to zoom in and out without losing context, automatic methods for map generalization are needed. We approach this problem for land-cover maps. Given two land-cover maps at two different scales, we want to find a sequence of small incremental changes that gradually transforms one map into the other. We assume that the two input maps consist of polygons, each of which belongs to a given land-cover type. Every polygon on the smaller-scale map is the union of a set of adjacent polygons on the larger-scale map. In each step of the computed sequence, the smallest area is merged with one of its neighbors. We do not select that neighbor according to a prescribed rule but compute the whole sequence of pairwise merges at once, based on global optimization. We have proved that this problem is NP-hard. We formalize this optimization problem as that of finding a shortest path in a (very large) graph. We present the A ⋆ algorithm and integer linear programming to solve this optimization problem. To avoid long computing times, we allow the two methods to return non-optimal results. In addition, we present a greedy algorithm as a benchmark. We tested the three methods with a dataset of the official German topographic database ATKIS. Our main result is that A ⋆ finds optimal aggregation sequences for more instances than the other two methods within a given time frame.

Radio environment maps for military cognitive networks: density of small-scale sensor network vs. map quality

In this paper, we present the dependency between density of a sensor network and map quality in the radio environment map (REM) concept. The architecture of REM supporting military communications systems is described. The map construction techniques based on spatial statistics and transmitter location determination are presented. The problem of REM quality and relevant metrics are discussed. The results of field tests for UHF range with a different number of sensors are shown. Exemplary REM maps with different interpolation algorithms are presented. Finally, the problem of density of a sensor network versus REM map quality is analyzed.

Possible futures of soil-mapping in France

The need for soil data has largely increased worldwide given the growing general concern about the maintenance and recovery of ecosystem resources and services. The development of digital soil mapping (DSM) is often seen as a means for answering this demand. In France, the national soil mapping strategy has been defined in the early 1990s within the Soil Inventory, Management and Conservation Programme (IGCS) and based on conventional soil mapping approaches. Now, small-scale soil map coverage of France has been almost achieved, soil data needs have evolved and DSM approaches have matured. The question therefore arises of what should be the future soil mapping strategy in France so as to foster soil mapping, better answer end-users needs and raise societal concern about soils. To answer this issue, we present in this paper a prospective analysis of the French national soil mapping strategy, which included i) a survey of the needs and difficulties expressed by producers, managers and users of soil data and ii) a foresight study of potential future scenarios for the development of soil mapping that takes advantage of DSM approaches. The survey indicated that soil information needs are high in terms of soil attributes, spatial resolution and accuracy and go beyond the data and maps presently available for France. The survey also showed that DSM methods remain little known outside the academic sector. The foresight study led to two main outputs. The first is to propose two complementary spatial sampling strategies for new data acquisition: i) upgrading the density of observed soil profiles to homogenize the accuracy of 1:250,000 soil maps for France and ii) improving the knowledge of local soil distribution patterns in the French regions by developing detailed mapping of reference areas, representative of the local soil patterns. The second output is a set of four possible scenarios for the development of soil mapping that differ according to the expected level of concern about soils that may exist in France in the future. The comparison of the scenarios led to several recommendations for favouring soil mapping, acquisition of new soil data and dissemination of soil knowledge. The recommendations include awareness raising about soil mapping and its potential for answering many environmental challenges, capacity building of soil surveyors and soil data users for DSM approaches, and improved quality assessment of soil maps to guide users and stimulate new investments of map producers. This certainly involves renewed public support before market development of soil mapping activities can take place and become the main support for soil mapping in France.

The cartographic visualisation of spatial data. An example of nature protection areas in the Podlaskie Voivodship (north-eastern Poland)

Abstract The authors attempt to visualise nature conservation issues in the Podlaskie Voivodship using a series of small-scale thematic maps. Publicly available spatial and statistical data was used. The authors discuss the effects of applying the adopted methodological solutions. Some of them present a new approach to cartographic visualisation of spatial data. It may be an opportunity to look at various visualisation methods, their effectiveness, and the possibility of visualising nature issues on small-scale thematic maps.

Spatial Disaggregation of Social Indicators: An Info-Metrics Approach

In this paper we propose a methodology to obtain social indicators at a detailed spatial scale by combining the information contained in census and sample surveys. Similarly to previous proposals, the method proposed here estimates a model at the sample level to later project it to the census scale. The main novelties of the technique presented are that (i) the small-scale mapping produced is perfectly consistent with the aggregates -regional or national- observed in the sample, and (ii) it does not require imposing strong distributional assumptions. The methodology suggested here follows the basics presented on Golan (2018) by adapting a cross-moment constrained Generalized Maximum Entropy (GME) estimator to the spatial disaggregation problem. This procedure is compared with the equivalent methodology of Tarozzi and Deaton (2009) by means of numerical experiments, providing a comparatively better performance. Additionally, the practical implementation of the methodology proposed is illustrated by estimating poverty rates for small areas for the region of Andalusia (Spain).

Soil Cover Diversity and Its Spatial Organization at Different Map Scales

We summarized the results of studies of pedodiversity and contrast and variability of soil properties based on the analyses of soil maps of different scales for the republics of Karelia and Dagestan and the Moscow region. We used fragments of the Soil Map of the Russian Federation on a scale of 1 : 2 500 000 as a small-scale map and three different medium-scale maps (from 1 : 300 000 to 1 : 500 000). Large-scale maps (1 : 10 000) were compiled for representative plots within the studied territories specifically for the study of pedodiversity. All the maps were digitized, map legends were converted to the new Russian soil classification system and to the World Reference Base for Soil Resources (WRB), and Shannon–Wiener diversity indices were calculated. Comparison of indicators revealed the dependence of the values of the diversity indices on the map scale. The indicators for the large-scale map were relatively low and did not differ much when using Russian and international classification. We concluded that for the successful assessment of soil diversity at different scales, it is important to use several large-scale maps that reflect the heterogeneity of regional soilscapes. Natural boundaries between soilscapes and soil regions can be found using the pedodiversity index map. In almost all cases, maps with a WRB-based legend had lower indicators of pedodiversity than maps with a legend based on the Russian soil classification. This confirms the fact that the international classification is less detailed than the Russian national classification, which was originally intended for large-scale mapping of soils.

Satellite Constellation Reveals Crop Growth Patterns and Improves Mapping Accuracy of Cropping Practices for Subtropical Small-Scale Fields in Japan

Mapping of agricultural crop types and practices is important for setting up agricultural production plans and environmental conservation measures. Sugarcane is a major tropical and subtropical crop; in general, it is grown in small fields with large spatio-temporal variations due to various crop management practices, and satellite observations of sugarcane cultivation areas are often obscured by clouds. Surface information with high spatio-temporal resolution obtained through the use of emerging satellite constellation technology can be used to track crop growth patterns with high resolution. In this study, we used Planet Dove imagery to reveal crop growth patterns and to map crop types and practices on subtropical Kumejima Island, Japan (lat. 26°21′01.1″ N, long. 126°46′16.0″ E). We eliminated misregistration between the red-green-blue (RGB) and near-infrared band imagery, and generated a time series of seven vegetation indices to track crop growth patterns. Using the Random Forest algorithm, we classified eight crop types and practices in the sugarcane. All the vegetation indices tested showed high classification accuracy, and the normalized difference vegetation index (NDVI) had an overall accuracy of 0.93 and Kappa of 0.92 range of accuracy for different crop types and practices in the study area. The results for the user’s and producer’s accuracy of each class were good. Analysis of the importance of variables indicated that five image sets are most important for achieving high classification accuracy: Two image sets of the spring and summer sugarcane plantings in each year of a two-year observation period, and one just before harvesting in the second year. We conclude that high-temporal-resolution time series images obtained by a satellite constellation are very effective in small-scale agricultural mapping with large spatio-temporal variations.