PlanetScope Satellite Research Articles

Application of PlanetScope-based Depth Invariant Index method in Seagrass Mapping: The study in Thi Nai Lagoon, Binh Dinh Province

The seagrass ecosystem is one of the most critical coastal and marine ecologies. The seagrass meadows can protect the seabed coastal erosion, absorb nutrients from coastal runoff and stabilize sediments, act as bio-filters, and provide a habitat for marine animals. Nevertheless, under the impact of socio-economic growth, seagrass in the Thi Nai lagoon has disappeared and been severely deteriorated. Therefore, mapping seagrass in this area is important in informing ecologists and economists to improve sustainable marine ecosystem management strategies. This study aims to detect seagrass in Thi Nai lagoon, Vietnam, by remote sensing method. PlanetScope (PS) satellite images have high spatial (3m) resolution that is applied to extract seagrass using Lyzenga's Depth Invariance Index technique for water column correction and Maximum Likelihood Classifier (MLC). After that, evaluate the accuracy of the results using field data collected from July 29, 2020, to August 1, 2021. The study results achieved high accuracy in isolating seagrass subjects with an overall accuracy of 85.09% and Cohen's Kappa value of 0.8. There are approximately 180 hectares of seagrass in the study area. Moreover, the results also show that seagrasses are mainly distributed on the sand, muddy sand, and sandy mud along the west shore of Thi Nai lagoon and dunes such as Con Chim, Con Trang, and Con Tau, with depths ranging from 1 to 2.5 meters (90.97 %).

Crop Yield Map Development Based on Satellite and UAV Data

Agriculture is one of the promising areas for the introduction of remote sensing technologies. With its help, you can timely receive a wide range of dynamic information about the conditions for the crops growth and development and make the necessary adjustments to obtain the planned result. The paper presents the results of early forecasting of spring wheat yields based on Dove (PlanetScope) satellite data from Planet Labs and DJI P4 Multispectral unmanned data. The maps of the yield of spring wheat were constructed using satellite and unmanned data with a spatial resolution of 3 m and 5 cm, respectively. A statistical assessment of the inhomogeneity of the spectral optical characteristics of agricultural crops has been carried out. The degree of correlation dependence between the value of the integral of the index (NDVI, VARI, MSAVI2, ClGreen) and the yield in different periods of the growing season has been determined.

Remote Sensing Classification of Urban Black-odor Water Based on Decision Tree

Remote sensing monitoring of black-odor water is an important method for understanding the current status of urban water quality, and comprehensively evaluating the effect of urban water environment treatment. A total of 171 samples were collected in Nanjing, Changzhou, Wuxi, and Yangzhou cities and water quality parameters and optical parameters were measured simultaneously. Based on the analysis of the water color and optical characteristics of the black-odor water and non-black-odor water (denoted as general water), a decision tree was constructed to identify the severe, mild black-odor water, and general water as green and yellow water. The results found that:①According to the water color, the water bodies can be divided into six types. Among them, type 1 to 4 water bodies are black-odor water, which are gray black, dark gray, gray, and light gray water, respectively, and type 5 and 6 water bodies are general water, which are green and yellow water, respectively; ②Type 1 water body contains high contents of non-pigmented particulate matter and colored dissolved organic matter(CDOM), however, the absorption of pigmented particulate matter is not dominant. Type 2 and 5 water bodies are dominated by pigmented particulate matter. Type 3, 4, and 6 water bodies are dominated by non-pigmented particulate matter; ③After water color classification, and according to the differences of the reflection spectrums of the six types of water bodies, the difference of black-odorous water index (DBWI), green-red-nir area water index (G-R-NIR AWI), the green band reflectance and the normalized difference black-odorous water index (NDBWI) were used to construct a decision tree to identify the severe, mild black-odor water, and general water; ④The decision tree was applied to the PlanetScope satellite image of Yangzhou City on April 9, 2019, and 10 synchronous sampling points were used for verification. The overall recognition accuracy reached 80.00%, and the K value reached 0.67. The urban water classification model, after water color classification, can be applied to other similar water bodies, and provides a technical method for the supervision of black-odor water bodies.

Spatiotemporal Dynamics and Environmental Controlling Factors of the Lake Tana Water Hyacinth in Ethiopia

The largest freshwater lake in Ethiopia, Lake Tana, has faced ecological disaster due to water hyacinth (Eichhornia crassipes) infestation. The water hyacinth is a threat not only to the ecology but also to the socioeconomic development of the region and cultural value of the lake, which is registered as a UNESCO reserve. This study aims to map the spatiotemporal dynamics of the water hyacinth using high-resolution PlanetScope satellite images and assesses the major environmental variables that relate to the weed spatial coverage dynamics for the period August 2017 to July 2018. The plausible environmental factors studied affecting the weed dynamics include lake level, water and air temperature, and turbidity. Water temperature and turbidity were estimated from the moderate resolution imaging spectroradiometer (MODIS) satellite image and the water level was estimated using Jason-1 altimetry data while the air temperature was obtained from the nearby meteorological station at Bahir Dar station. The results indicated that water hyacinth coverage was increasing at a rate of 14 ha/day from August to November of 2017. On the other hand, the coverage reduced at a rate of 6 ha/day from December 2017 to June 2018. However, the length of shoreline infestation increased significantly from 4.3 km in August 2017 to 23.4 km in April 2018. Lake level and night-time water temperatures were strongly correlated with water hyacinth spatial coverage (p < 0.05). A drop in the lake water level resulted in a considerable reduction of the infested area, which is also related to decreasing nutrient levels in the water. The water hyacinth expansion dynamics could be altered by treating the nutrient-rich runoff with best management practices along the wetland and in the lake watershed landscape.

Spatial Distribution of NDVI Seeds of Cereal Crops with Different Levels of Weediness According to PlanetScope Satellite Data

The objective of the study is to assess the state of agricultural seeds (level of weediness) on the territory of the Krasnoyarsk Agricultural Research Institute of Federal Research Center «Krasnoyarsk Science Center of the SB RAS» near the village Minino according to satellite data. For this purpose, an algorithm for obtaining and processing PlaneScope satellite data for calculating the NDVI vegetation index of agricultural seeds has been developed. On its basis a map of the spatial distribution of NDVI wheat seeds with different levels of weediness has been created. According to PlanetScope satellite data, an opportunity to interpret areas of wheat seeds with high and low levels of weediness has been shown. It has been found that the NDVI value of pure plantation of wheat with a low level of weediness is greater than the NDVI value of wheat seeds with a high level of weediness

Temperature Dynamics Assessment of Agricultural Objects Based on Unmanned Aircraft Data

During the study, the spatial and temporal distribution of radiant temperature of agricultural fields has been made. The object of the study is agricultural fields (barley, oats, fallow field, perennial grasses (Onobrychis)), located on the territory of the Krasnoyarsk Research Institute of Agriculture of the FRC KSC SB RAS near the village of Minino (Central Siberia, Krasnoyarsk region). The radiant temperature measurement of objects surface was taken by the ZENMUSE XT2 camera installed on the unmanned aircraft DJI Matrice 210 RTK V2. The spatial resolution of the obtained thermal maps is 12 – 14 cm. The state of the objects (the presence of vegetation cover) was assessed using the NDVI values obtained from the PlanetScope satellite data with a spatial resolution of 3 meters. It was established that the presence of plants and the size of their projective cover are decisive in the formation of soil cover temperature conditions. The growth and development of the vegetation cover, its height and closeness, change the temperature regime conditions. Instead of a soil, vegetation cover becomes an active surface. The thermal maps (spatial distribution of radiant temperature) of the agricultural land surface has been carried out, which makes it possible to assess the in-field temperature heterogeneity of the objects

A Hierarchical Deep-Learning Approach for Rapid Windthrow Detection on PlanetScope and High-Resolution Aerial Image Data

Forest damage due to storms causes economic loss and requires a fast response to prevent further damage such as bark beetle infestations. By using Convolutional Neural Networks (CNNs) in conjunction with a GIS, we aim at completely streamlining the detection and mapping process for forest agencies. We developed and tested different CNNs for rapid windthrow detection based on PlanetScope satellite data and high-resolution aerial image data. Depending on the meteorological situation after the storm, PlanetScope data might be rapidly available due to its high temporal resolution, while the acquisition of high-resolution airborne data often takes weeks to a month and is, therefore, used in a second step for more detailed mapping. The study area is located in Bavaria, Germany (ca. 165 km2), and labels for damaged areas were provided by the Bavarian State Institute of Forestry (LWF). Modifications of a U-Net architecture were compared to other approaches using transfer learning (e.g., VGG19) to find the most efficient architecture for the task on both datasets while keeping the computational time low. A custom implementation of U-Net proved to be more accurate than transfer learning, especially on medium (3 m) resolution PlanetScope imagery (intersection over union score (IoU) 0.55) where transfer learning completely failed. Results for transfer learning based on VGG19 on high-resolution aerial image data are comparable to results from the custom U-Net architecture (IoU 0.76 vs. 0.73). When using both architectures on a dataset from a different area (located in Hesse, Germany), however, we find that the custom implementations have problems generalizing on aerial image data while VGG19 still detects most damage in these images. For PlanetScope data, VGG19 again fails while U-Net achieves reasonable mappings. Results highlight the potential of Deep Learning algorithms to detect damaged areas with an IoU of 0.73 on airborne data and 0.55 on Planet Dove data. The proposed workflow with complete integration into ArcGIS is well-suited for rapid first assessments after a storm event that allows for better planning of the flight campaign followed by detailed mapping in a second stage.

Agricultural Landscape Composition Linked with Acoustic Measures of Avian Diversity

Measuring, monitoring, and managing biodiversity across agricultural regions depends on methods that can combine high-resolution mapping of landscape patterns with local biodiversity observations. This study explores the potential to monitor biodiversity in agricultural landscapes by linking high-resolution remote sensing with passive acoustic monitoring. Land cover maps produced using a small unmanned aerial system (UAS) and PlanetScope (PS) satellite imagery were used to investigate relationships between landscape patterns and an acoustically derived biodiversity index (vocalizing bird species richness) across 12 agricultural sample locations equipped with acoustic recorders in Iowa, USA during the 2018 growing season. Statistical assessment revealed a significant direct association between vocalizing bird richness and percent noncrop vegetation cover. High spatial resolution (1 m) UAS mapping produced stronger statistical associations than PS-based maps (3 m) for landscape composition metrics. Landscape configuration metrics (Shannon’s diversity index, contagion, perimeter-area-ratio, and circumscribing circle index) were either cross-correlated with composition metrics or unusable owing to complete landscape homogeneity in some agricultural landscape samples. This study shows that high resolution mapping of noncrop vegetation cover can be linked with acoustic monitoring of unique bird vocalizations to provide a useful indicator of biodiversity in agricultural landscapes.

Assessing the effect of spatial resolution on the delineation of management zones for smallholder farming in southern Brazil

Remote sensing estimates of cover-crop aboveground biomass (AGB) have been used to delineate management zones for smallholder farming in southern Brazil. In this study, we investigated the spatial resolution influence on the AGB estimates of rye, calculated from regression relationships with the Normalized Difference Vegetation Index (NDVI), and on the subsequent delineation of management zones using the Management Zone Analyst (MZA) software. Data acquired by an Unmanned Aerial Vehicle (UAV) Parrot Sequoia camera (0.20 m spatial resolution) in Brazil were compared with observations from the PlanetScope (PS) satellite constellation (3 m) and the Operational Land Imager (OLI)/Landsat-8 (30 m). A three-endmember mixture model (green vegetation, soil, and shadow) was applied to surface reflectance data of these instruments for evaluating the cover-crop development at two dates in August 2017. Because of the differences in the technical specifications of the sensors, we resampled the UAV dataset into four levels of spatial resolution (1, 3, 10, and 30 m). Using the UAV map (0.20 m) as a reference, we obtained confusion matrices for the original and resampled data. The results showed that the increasing amounts of rye AGB from the beginning to the end of August promoted significant changes in surface reflectance and in soil-green vegetation fractions calculated at variable spatial resolution. The performance of the regression models to estimate cover-crop AGB was approximately similar in the transition from the sub-metric (0.20 m) to the metric (3 m) spatial resolutions, or from the UAV camera to the PS data. For all datasets, the MZA detected two management zones with zone 2 having higher cover-crop AGB than zone 1. When compared to the UAV management zone map (reference), the PS map had a moderate-to-substantial agreement, while the OLI/Landsat-8 map had a fair-to-moderate concordance. Substantial agreements with the reference map were observed at simulated 1 m and 3 m data, as indicated by Kappa coefficients of 0.73 and 0.63 and overall accuracies of 86.40% and 81.40%, respectively. We conclude that the 3 m spatial resolution data of the PS comprise an alternative to delineate management zones for smallholder farming in southern Brazil when compared to the very-high spatial resolution observations of the UAV cameras.

Building Footprint Generation by Integrating Convolution Neural Network With Feature Pairwise Conditional Random Field (FPCRF)

Building footprint maps are vital to many remote sensing applications, such as 3D building modeling, urban planning, and disaster management. Due to the complexity of buildings, the accurate and reliable generation of the building footprint from remote sensing imagery is still a challenging task. In this work, an end-to-end building footprint generation approach that integrates convolution neural network (CNN) and graph model is proposed. CNN serves as the feature extractor, while the graph model can take spatial correlation into consideration. Moreover, we propose to implement the feature pairwise conditional random field (FPCRF) as a graph model to preserve sharp boundaries and fine-grained segmentation. Experiments are conducted on four different datasets: (1) Planetscope satellite imagery of the cities of Munich, Paris, Rome, and Zurich; (2) ISPRS benchmark data from the city of Potsdam, (3) Dstl Kaggle dataset; and (4) Inria Aerial Image Labeling data of Austin, Chicago, Kitsap County, Western Tyrol, and Vienna. It is found that the proposed end-to-end building footprint generation framework with the FPCRF as the graph model can further improve the accuracy of building footprint generation by using only CNN, which is the current state-of-the-art.

Exploring the Potential of High-Resolution Satellite Imagery for the Detection of Soybean Sudden Death Syndrome

Sudden death syndrome (SDS) is one of the major yield-limiting soybean diseases in the Midwestern United States. Effective management for SDS requires accurate detection in soybean fields. Since traditional scouting methods are time-consuming, labor-intensive, and often destructive, alternative methods to monitor SDS in large soybean fields are needed. This study explores the potential of using high-resolution (3 m) PlanetScope satellite imagery for detection of SDS using the random forest classification algorithm. Image data from blue, green, red, and near-infrared (NIR) spectral bands, the calculated normalized difference vegetation index (NDVI), and crop rotation information were used to detect healthy and SDS-infected quadrats in a soybean field experiment with different rotation treatments, located in Boone County, Iowa. Datasets collected during the 2016, 2017, and 2018 soybean growing seasons were analyzed. The results indicate that spectral features, when combined with ground-based information, can detect areas in soybean plots that are at risk for disease, even before foliar symptoms develop. The classification of healthy and diseased soybean quadrats was >75% accurate and the area under the receiver operating characteristic curve (AUROC) was >70%. Our results indicate that high-resolution satellite imagery and random forest analyses have the potential to detect SDS in soybean fields, and that this approach may facilitate large-scale monitoring of SDS (and possibly other economically important soybean diseases). It may also be useful for guiding recommendations for site-specific management in current and future seasons.

FROM PIXEL TO YIELD: FORECASTING POTATO PRODUCTIVITY IN LEBANON AND IDAHO

Abstract. Idaho and Lebanon rely on potatoes as an economically important crop. NDVI (Normalized Difference Vegetation Index), GNDVI (Green Normalized Difference Vegetation Index), SAVI (Soil Adjusted Vegetation Index), and MSAVI2 (Modified Soil Adjusted Vegetation Index 2) indices were calculated from PlanetScope satellite imagery for the 2017 growing season cloud free days. Variations in vegetation health were tracked over time and correlated to yield data provided by growers in Idaho. Based on ordinary least squares regression an Idaho yield forecast model was developed. Vegetation response during the growth stage at which potato tubers were filling out was significant in predicting yield for both the Norkotah and Russet potato variety. This corresponded to a week with high recorded temperatures that impacted the health status of the crops. The yield forecasting model was validated with a cross validation approach and then applied to potato fields in Lebanon. The Idaho model successfully displayed yield variation in crops for Lebanon. Spectral indices along with field topography allow the prediction of yield based on the crop type and variety.

Detecting northern peatland vegetation patterns at ultra‐high spatial resolution

AbstractWithin northern peatlands, landscape elements such as vegetation and topography are spatially heterogenic from ultra‐high (centimeter level) to coarse scale. In addition to within‐site spatial heterogeneity, there is evident between‐site heterogeneity, but there is a lack of studies assessing whether different combinations of remotely sensed features and mapping approaches are needed in different types of landscapes. We evaluated the value of different mapping methods and remote sensing datasets and analyzed the kinds of differences present in vegetation patterns and their mappability between three northern boreal peatland landscapes in northern Finland. We utilized field‐inventoried vegetation plots together with spectral, textural, topography and vegetation height remote sensing data from 0.02‐ to 3‐m pixel size. Remote sensing data included true‐color unmanned aerial vehicle images, aerial images with four spectral bands, aerial lidar data and multiple PlanetScope satellite images. We used random forest regressions for tracking plant functional type (PFT) coverage, non‐metric multidimensional scaling ordination axes and fuzzy k‐medoid plant community clusters. PFT regressions had variable performance for different study sites (R2 −0.03 to 0.69). Spatial patterns of some spectrally or structurally distinctive PFTs could be predicted relatively well. The first ordination axis represented wetness gradient and was well predicted using remotely sensed data (R2 0.64 to 0.82), but the other three axes had a less straightforward explanation and lower mapping performance (R2 −0.09 to 0.53). Plant community clusters were predicted most accurately in the sites with clear string‐flark topography but less accurately in the flatter site (R2 0.16–0.82). The most important remote sensing features differed between dependent variables and study sites: different topographic, spectral and textural features; and coarse‐scale and fine‐scale datasets were the most important in different tasks. We suggest that multiple different mapping approaches should be tested and several remote sensing datasets used when maps of vegetation are produced.

Oil Spill Detection from PlanetScope Satellite Image: Application to Oil Spill Accident near Ras Al Zour Area, Kuwait in August 2017

Park, S.-H.; Jung, H.-S.; Lee, M.-J.; Lee, W.-J., and Choi, M.-J., 2019. Oil spill detection from PlanetScope satellite image: Application to oil spill accident near Ras Al Zour area, Kuwait in August 2017. In: Jung, H.-S.; Lee, S.; Ryu, J.-H., and Cui, T. (eds.), Advances in Remote Sensing and Geoscience Information Systems of Coastal Environments. Journal of Coastal Research, Special Issue No. 90, pp. 251-260. Coconut Creek (Florida), ISSN 0749-0208.Oil spill accidents are major marine disasters that can destroy the ocean ecosystem. Satellite images are widely used to respond immediately to oil spill accidents. A miniaturized satellite equipped with an optical sensor has an advantage that the imaging period is very short because a large number of satellites can be operated. In this study, oil slick areas were detected by applying the artificial neural network (ANN) technique to the PlanetScope satellite optical image captured near Ras Al Zour, Kuwait on August 10, 2017. However, the image included sunglint effects owing to ocean waves and yellow dust areas, making it difficult to classify the oil slick area. In addition, the spilled oil had three different spectral information characteristics through interaction with the sea surface of the Persian Gulf. The image processing was divided into the pre-processing step and the oil slick classification step to detect the oil slick area and to mitigate these limitations. In the pre-processing step, a directional median filter was applied to reduce the sunglint effects caused by ocean waves, and the negative effects from the sea surface and dust were mitigated using the differences with the low-pass filtered image. In the oil slick detection step, three types of oil probability maps and one sea surface probability map were produced using the ANN technique. Subsequently, an oil slick classification map was produced by applying the maximum probability choosing method and dust area rejection. Through validation, the overall accuracy of the oil classification map was obtained to be 82.01 % and the kappa coefficient was 72.42 %. The proposed oil detection method can effectively detect different types of oil spill areas in optical images with sunglint and dust handicaps. Moreover, it has high potential to be used in the future because the revisit time of the satellite image used is shorter than that of other optical images.

Machine Learning Application for Coastal Area Change Detection in Gangwon Province, South Korea Using High-Resolution Satellite Imagery

Park, S.-J.; Achmad, A.R.; Syifa, M., and Lee, C.-W., 2019. Machine learning application for coastal area change detection in Gangwon province, South Korea using high-resolution satellite imagery. In: Jung, H.-S.; Lee, S.; Ryu, J.-H., and Cui, T. (eds.), Advances in Remote Sensing and Geoscience Information Systems of Coastal Environments. Journal of Coastal Research, Special Issue No. 90, pp. 228-235. Coconut Creek (Florida), ISSN 0749-0208.The coastal area is one of an essential region for the ecosystem. Various kinds of effects that occur due to natural phenomena and human intervention make an impact on the change in the coastal area. In recent years, coastal erosion caused severe problems along the Korea coastline with 143 sites are experienced erosion throughout 2013. In this study, six beaches from 3 cities in Gangwon province, Republic of Korea are chosen to monitor its coastal area in 2016 and 2018. Those areas were chosen due to the high erosion severity grades according to Coastal Maintenance Project of the Ministry of Land, Infrastructure, and Transport. By using a support vector machine (SVM) classifier, high-resolution imagery from PlanetScope satellite was processed to generate the map that separate coastal area with others. The coastal area is successfully detected and calculated using SVM classifier. The result of the coastal area map is beneficial for the government or the authorities as mitigation and prevention plan.

Spatial distribution of submerged aquatic vegetation in An Chan coastal waters, Phu Yen province using the PlanetScope satellite image

Seaweed and seagrass form marine submerged aquatic vegetation (SAV), which plays an essential role in economic development and ecological protection in coastal areas. In this study, PlanetScope (PS )imaging data was combined with in situ samplings to demonstrate their ability to map SAV distribution in An Chan commune, Tuy An district, Phu Yen province, Central Vietnam. Thanks to data pre-processing by Lyzenga’s algorithm and the masking in PS image allow us to remove partly the signals of spectral noises from sun glint effect as well as other random noises. The analysis and accuracy assessment of SAV classification by four different techniques: DII, enhanced DII, BRI and enhanced BRI were alternately performed. The overall accuracy in the accuracy assessment of SAV classification by the above techniques were alternately 83.33%, 88.58%, 86.17%, and 92.52% respectively. Kappa coefficients in the accuracy assessment of SAV classification by the above techniques were alternately 0.77, 0.84, 0.81 and 0.90 respectively. The results of SAV classification by enhanced BRI technique provided the best accuracies and will be chosen for assessing the distribution of Submerge Aquatic Vegetation (SAV) canopies in An Chan coastal waters from PS satellite image. The seagrass beds in An Chan is spread along the coast as well as lie close to the coast of islets. Whereas, the seaweed meadows lie in deeper waters and in the foot of the reefs in 3–4m deep. The total seagrass area in An Chan region was approximately 12.22 ha, with 10.93 ha seagrasses in My Quang, 1.18 ha in Hon Chua and 0.11 ha in Hon Dua. The total seaweed area in An Chan region was approximately 50.32 ha, with 20.20 ha seaweed meadows in My Quang, 22.8 ha in Hon Chua, 5.72 ha in Hon Dua and a small part of 1.60 ha in underwater small reefs.

An anthropogenic landslide dammed the Songmai River, a tributary of the Jinsha River in Southwestern China

On March 20, 2019, a landslide (named Yagu landslide) occurred in eastern Tibetan Plateau. It produced a 10-m-high dam, resulting in a lake on the Songmai River, a tributary of the Jinsha River. This paper describes this slope failure and analyzes the process and cause of the landsliding based on the combination of Google Earth images, PlanetScope satellite optical images, field photography and geologic data. It is speculated that this event was likely induced by local human activity, such as quarrying rather than natural factors. This example raises a challenging issue whether the ongoing projects along the Jinsha River can induce landslides. In addition, the emergency responses of the government and the effort for risk removal of the dammed lake are presented.

Data and resolution requirements in mapping vegetation in spatially heterogeneous landscapes

It has been argued that even centimeter-level resolution is needed for mapping vegetation patterns in spatially heterogeneous landscapes such as northern peatlands. However, there are few systematic tests for determining what kind of spatial resolution and data combinations are needed and what the differences in mapping accuracy are when different datasets are omitted or included. We conducted 78 different object-based supervised random forest classifications on a patterned fen and its surroundings in Kaamanen, northern Finland, using remotely sensed optical imagery, topography, and vegetation height datasets from different platforms (unmanned aerial vehicle (UAV), aerial, satellite) with spatial resolution ranging from 5 cm to 3 m. We compared differences in classification performance when we altered (1) classification and segmentation input data and features calculated from the data, or (2) the segmentation scale. We constructed training data with the help of transect-based field sampling and UAV imagery and tested classification accuracy using 412 field-surveyed vegetation plots. The most accurate classifications (75.7% overall accuracy) were obtained when we segmented a 5 cm resolution UAV image with a small segmentation scale and calculated features from all datasets. Classification accuracy was 2.2 percentage points (pp) lower with the most accurate aerial image (50 cm resolution) based classification, and 7.6 pp and 11.9 pp lower with the most accurate WorldView-2 (2 m resolution) and PlanetScope (3 m resolution) satellite image based classifications respectively. Classification accuracies were low (46.7–56.0%) when we used only spectral data from one dataset. The inclusion of gray-level co-occurrence matrix textural features increased classification accuracy by 0.4–12.1 pp and inclusion of multiple datasets by 8.2–25.0 pp. Segmentation scale had a minor effect on classification accuracy (2.5–7.3 pp difference between the finest and coarsest segmentation scale); however, both too small and large segmentation scale might lead to suboptimal classification. The differences in land cover type areal coverage were relatively small between classifications with multiple datasets, but if classifications included features from only one dataset, the differences were larger. We conclude that multiple different optical, topographical, and vegetation height datasets should be used when mapping vegetation in spatially heterogeneous landscapes, and that sub-meter resolution data (e.g. UAV or aerial) are necessary for the most accurate maps. Although UAV data is not essentially needed for classification, it is useful for training dataset construction and especially helpful in areas lacking other sub-meter resolution data.

Estimating Rangeland Forage Production Using Remote Sensing Data from a Small Unmanned Aerial System (sUAS) and PlanetScope Satellite

Rangelands cover ~23 million hectares and support a $3.4 billion annual cattle industry in California. Large variations in forage production from year to year and across the landscape make grazing management difficult. We here developed optimized methods to map high-resolution forage production using multispectral remote sensing imagery. We conducted monthly flights using a Small Unmanned Aerial System (sUAS) in 2017 and 2018 over a 10-ha deferred grazing rangeland. Daily maps of NDVI at 30-cm resolution were first derived by fusing monthly 30-cm sUAS imagery and more frequent 3-m PlanetScope satellite observations. We estimated aboveground net primary production as a product of absorbed photosynthetically active radiation (APAR) derived from NDVI and light use efficiency (LUE), optimized as a function of topography and climate stressors. The estimated forage production agreed well with field measurements having a R2 of 0.80 and RMSE of 542 kg/ha. Cumulative NDVI and APAR were less correlated with measured biomass ( R 2 = 0.68). Daily forage production maps captured similar seasonal and spatial patterns compared to field-based biomass measurements. Our study demonstrated the utility of aerial and satellite remote sensing technology in supporting adaptive rangeland management, especially during an era of climatic extremes, by providing spatially explicit and near-real-time forage production estimates.

Assessment of thermal conditions in Krasnoyarsk urban area with use of different satellite data and geographic information system

Satellite data in the thermal infrared range are a powerful source of information for the analysis and determination of city urban area temperature anomalies. The article presents a technique for monitoring the land surface temperature on the basis of combination of ?Landsat 8? satellite thermal infrared data with PlanetScope satellite constellation high resolution data. Such combination of satellite data from several spacecrafts increase the detalization of temperature maps to the level of individual city blocks. Determination of the nature and boundaries of temperature anomalies will help to understand the causes of the unfavorable environmental situation in Krasnoyarsk, where, in addition to high industrial emissions, their influence and atmospheric processes, leading to the fact that impurities are delayed and concentrated over the city. The results shows that the temperature in the places of thermal anomalies is 5?-8? higher than the average land surface temperature of the city. Based on the results of the analysis of summer thermal multi-temporal space images, several thermal zones of different nature were outlined on the territory under consideration. This information can be used in planning the development of the city, the design of new urban neighborhoods.