Time Series Of Imagery Research Articles

Mapping of Cotton Fields Within-Season Using Phenology-Based Metrics Derived from a Time Series of Landsat Imagery

A phenology-based crop type mapping approach was carried out to map cotton fields throughout the cotton-growing areas of eastern Australia. The workflow was implemented in the Google Earth Engine (GEE) platform, as it is time efficient and does not require processing in multiple platforms to complete the classification steps. A time series of Normalised Difference Vegetation Index (NDVI) imagery were generated from Landsat 8 Surface Reflectance Tier 1 (L8SR) and processed using Fourier transformation. This was used to produce the harmonised-NDVI (H-NDVI) from the original NDVI, and then phase and amplitude values were generated from the H-NDVI to visualise active cotton in the targeted fields. Random Forest (RF) models were built to classify cotton at early, mid and late growth stages to assess the ability of the model to classify cotton as the season progresses, with phase, amplitude and other individual bands as predictors. Results obtained from leave-one-season-out cross validation (LOSOCV) indicated that Overall Accuracy (OA), Kappa, Producer’s Accuracies (PA) and User’s Accuracy (UA), increased significantly when adding amplitude and phase as predictor variables to the model, than prediction using H-NDVI or raw bands only. Commission and omission errors were reduced significantly as the season progressed and more in-season imagery was available. The methodology proposed in this study can map cotton crops accurately based on the reconstruction of the unique cotton reflectance trajectory through time. This study confirms the importance of phenological metrics in improving in-season cotton fields mapping across eastern Australia. This model can be used in conjunction with other datasets to forecast yield based on the mapped crop type for improved decision making related to supply chain logistics and seasonal outlooks for production.

Assessing the impact of land use and land cover dynamics on water quality of Dal Lake, NW Himalaya, India

A dynamic process like land use, if anthropogenically unsustainable, adversely affects the well-being of the land system. Worldwide, water bodies are facing imminent threat due to unsustainable anthropogenic activities. Water quality and ecology are the two characteristics of water bodies, if not preserved, shall have a direct consequence on the well-being of the human systems. Hence it is essential to understand the causes and consequences of the deteriorating water body systems. The condition is particularly grim in Himalayan water body ecosystems, where unplanned and unchecked urbanization has threatened their very existence. In the present study, the dynamics of land use/land cover (LULC) and its impact on the water quality of Dal Lake in Kashmir Himalaya, India has been assessed. We carried out a detailed study wherein changing LULC is analyzed against the deteriorating trophic status of the Dal Lake using time-series of satellite imagery of the lake’s catchment and its water quality data. Results indicated that the water quality of Dal Lake has remarkably deteriorated due to increased nutrient and sediment loads from the catchment, attributed to significant anthropogenic activities in the catchment. Due to unprecedented LULC changes in the catchment, the forest class shows a significantly negative change since the last four decades (1980–2018), corroborating with the ongoing deterioration of physicochemical characteristics of the lake. The analysis shows an increase in all the agents of eutrophication, such as NO3–N, TP, and COD, from 1990 to 2018. The decrease in forest, agriculture, and floating gardens was observed to show a significant negative correlation with the increase in the decadal average values of the COD, NO3–N, and TP for the same corresponding period. Similarly, a positive correlation was found between the increase in built-up, aquatic vegetation, bare surfaces, and these water quality parameters, establishing a strong relationship between the deteriorating condition of the lake and changing LULC. Our findings indicate that changing LULC of the lake’s catchment is one of the critical factors that has significantly contributed toward the deteriorating ecology and water quality of the Dal Lake. This study shall contribute toward the development of the robust conservation strategy in order to save this urban lake from its untimely death.

Topographic, edaphic and climate influences on aspen (Populus tremuloides) drought stress on an intermountain bunchgrass prairie

Quaking aspen, Populus tremuloides, has experienced severe declines in recent years in part due to the effects of changing climate and extreme drought. This study set out to investigate these effects by assessing associations of climatic, edaphic and topographic variables with physiological drought stress in aspen. The study took place on the Zumwalt Prairie in northeastern Oregon, a semi-arid bunchgrass prairie where aspen occur in isolated stands associated with riparian areas and late-season persistence of snow drifts. Using a 33-year time series of Landsat imagery to detect associations of aspen stands late-season snow cover and field measurements of soil moisture in aspen stands during 2017, we found while snow dominated stands were associated with greater soil moisture during spring, levels had equilibrated to those of other upland stands by summer. Measurements of predawn and midday stem Ψ in multiple height classes of aspen ramets revealed associations of both shallow soil moisture and vapor pressure deficit with physiological drought stress in aspen. Analysis of soil texture class revealed an important association with midday stem Ψ, with finer textured soils associated with decreased stem Ψ in comparison to coarser textured soils. While neither topographical characteristics nor snow cover were found to be important drivers of drought stress, topographical curvature was found to have a strong influence on summer soil moisture in upland stands. These findings contribute to our understanding of aspen physiology, drought ecology and landscape hydrology toward the xeric margin of aspen’s range. This information can help land managers anticipate and adapt to changing climates and understand their effects on key plant species such as aspen.

Institutional shifts and landscape change: the impact of the Período Especial on Cuba’s land system architecture

ABSTRACT Formal institutions, especially policies, play a key role in land system change. Compared to other drivers of change, however, the impact of policies on landscapes is under-addressed in land system science, in part due to difficulties isolating their effect on longitudinal land change. We address this gap by examining land system architecture changes in Cuba brought about by the 1991 collapse of the Soviet Union and the resulting economic crisis: El Período Especial (‘Special Period’). Employing a satellite imagery time-series alongside a review of policy documents, we identify statistically significant land system changes linked to the era’s institutional shifts. We find that concentrated policy efforts to transform agriculture and protect forests corresponded to considerable changes for agriculture but minimal changes to forests. Some changes resulting from the institutional shifts of the Período Especial became visible in the landscape as soon as a few years, while others took decades to manifest.

Landslides detection in Bat Xat district, Lao Cai province, Vietnam using the Alos PalSAR time-series imagery by the SBAS method

Radar Interferometry (InSAR) has been known as a technology to monitor the change of elements on the earth's surface for many years. There are many InSAR methods, in which the permanent scattering InSAR Radar (PSInSAR) method uses a series of images to determine the terrain deformetions quite well. However, for areas with lots of vegetation, the number of permanent scattering points (PS points) will be limited. In this paper, we have chosen a method that also uses a set of multi-temporal Radar images but has the lowest spatial and temporal image baselines, this method is called the Small Baselines method (SBAS). With the ALOS PalSAR images series that was collected from August 2007 to November 2010, many landslide points in the area of Bat Xat district, Lao Cai province were discovered. The landslide locations detected from Radar images were compared with the landslide surveying points and landslide interpreted by aerial photos in 2013 provided by Vietnam Institute of Geosciences and Mineral Resources Vietnam. There have been many sliding sites coinsiding with the surveyed landslides, which proves that many landslides exist and develop continuously such as the location of Mong Sen bridge, Trung Chai Commune or at Sai Duan bridge, Phin Ngan commune.

Exploring the potential of land surface phenology and seasonal cloud free composites of one year of Sentinel-2 imagery for tree species mapping in a mountainous region

Optical satellite imagery with high temporal and spatial resolution, such as acquired by Sentinel-2, is increasingly becoming available and is used to derive maps of tree species. Such mapping products are required in the scope of operational and sustainable forest management. Existing studies that employ Sentinel-2 imagery have already evaluated different classification algorithms but are often confined to areas smaller than a single Sentinel-2 scene. In this study, the area of interest (a large part of the Province of Tyrol (Austria)) is covered by two Sentinel-2 tiles, of which approximately 5000 km² are forested. In order to deal with seasonal metrics under recurrent cloud cover conditions, we exploit one year of Sentinel-2 imagery by using land surface phenology (LSP) and seasonal cloud-free composites for mapping five different tree species groups (Broadleaved-, Larch- (Larix), Pine- (Pinus), Dwarf Pine- (Pinus mugo) and Spruce/Fir (Abies alba/Picea abies) stands). Although a regular multitemporal classification setup based on three cloud-free images reached an overall accuracy of around 84.4 % and outperformed monotemporal setups by around 10 % points, the availability of single cloud-free images was limited in the mountainous region. Thus, alternative approaches, using combined measures for the entire time series of Sentinel-2 imagery, i.e. three-monthly temporal reflectance composites and phenological metrics, were tested and could even improve overall accuracy by 1–2 % points. As a conclusion, we agree with previous studies that multitemporal imagery can help improving the mapping accuracy. However, leveraging satellite image time series for large-scale mapping of tree species should not only rely on high-quality cloud-free single images and should strongly be supported by i.e. seasonal composites or multi-image metrics. Therefore, development and provisioning of such datasets should be fostered.

A NOVEL INDEX FOR TEMPORAL STABILITY ANALYSIS IN SPACE AND TIME OF SAR-DERIVED SCENES

Abstract. Detecting temporal changes is one of the most important applications of satellite sensors. In recent years, the increasing availability of regular time-series of SAR imagery, provided by the Sentinel-1 mission of the European Space Agency (ESA), has drawn increasing attention to these techniques, especially in earth environment monitoring and risk management. Within this paper, a coherent change detection analysis for evaluating the risk due to movements of dunes and sand sheets in desertic areas is proposed. To this purpose, we introduce a novel, coherence-based index, named Temporal Stability Index (TSI), that is suited for characterizing the percentage of stability of a target with time. TSI maps can be generated over areas as wide as hundreds of kilometers, in a short time, and mostly by exploiting available software tools (plus some simple coding). The information provided is complementary to the average of the short-term coherence, here shown. Results of analysis performed on two desertic regions (the United Arab Emirates and Egypt) document the usefulness of TSI for the identification of dune movements and areas subject to sand accumulation, supporting risk mitigation measures.

EXPLOITING SENTINEL-1 SAR TIME SERIES TO DETECT GRASSLANDS IN THE NORTHERN BRAZILIAN AMAZON

Abstract. Recent advances in cloud-computing technologies and remote sensing data availability foster the development of studies based on the analysis of optical and SAR imagery time series. In this paper, we assess the potential of Sentinel-1 imagery time series for grassland detection in the northern Brazilian Amazon. We used the Google Earth Engine cloud-computing platform as an alternative to obtain and analyse Sentinel-1 imagery, acquired from 2017 to 2018 over the region of Mojuí dos Campos/PA, Brazil. We extracted several temporal metrics from the imagery time series and used the Random Forest algorithm to perform the classification. In addition, we analysed the time series considering different channels, including the VV and VH polarizations, both separately and in combination, and the CR, RGI and NL indices. We could efficiently discriminate areas of grasslands from forest and agricultural crops using either VH time features or features extracted from the combination of both VV and VH polarizations. The classification map that resulted from the combination of VV and VH data presented the highest accuracy, with an overall accuracy of 95.33% and a 0.93 kappa index. Despite simple, the approach adopted in this paper showed potential to differ grasslands from areas of agriculture and forest in the northern Brazilian Amazon.

USING MULTITEMPORAL HYPER- AND MULTISPECTRAL UAV IMAGING FOR DETECTING BARK BEETLE INFESTATION ON NORWAY SPRUCE

Abstract. Various biotic and abiotic stresses are threatening forests. Modern remote sensing technologies provide powerful means for monitoring forest health, and provide a sustainable basis for forest management and protection. The objective of this study was to develop unmanned aerial vehicle (UAV) based spectral remote sensing technologies for tree health assessment, particularly, for detecting the European spruce bark beetle (Ips typographus L.) attacks. Our focus was to study the early detection of bark beetle attack, i.e. the “green attack” phase. This is a difficult remote sensing task as there does not exist distinct symptoms that can be observed by the human eye. A test site in a Norway spruce (Picea abies (L.) Karst.) dominated forest was established in Southern-Finland in summer 2019. It had an emergent bark beetle outbreak and it was also suffering from other stress factors, especially the root and butt rot (Heterobasidion annosum (Fr.) Bref. s. lato). Altogether seven multitemporal hyper- and multispectral UAV remote sensing datasets were captured from the area in August to October 2019. Firstly, we explored deterioration of tree health and development of spectral symptoms using a time series of UAV hyperspectral imagery. Secondly, we trained assessed a machine learning model for classification of spruce health into classes of “bark beetle green attack”, “root-rot”, and “healthy”. Finally, we demonstrated the use of the model in tree health mapping in a test area. Our preliminary results were promising and indicated that the green attack phase could be detected using the accurately calibrated spectral image data.

Multiple-feature-driven co-training method for crop mapping based on remote sensing time series imagery

ABSTRACT Remote sensing time series imagery (RSTSI) provides a useful tool for crop mapping, as it provides crucial spectral, temporal, and spatial (STS) features. However, its high dimensionality coupled with the limited number of training samples leads to an ill-posed classification problem and the Hughes phenomenon. To solve this problem, this study presents a multiple-feature-driven co-training method (MFDC) for accurately mapping crop types based on RSTSI with a limited number of training samples. In MFDC, four complementary pre-defined views, which represent STS features, are generated for the utilization of multiple features. Then, to enhance the classifier’s generalization ability, a novel labelled sample augmentation method that combines the Breaking Tiles algorithm and co-training is proposed. Third, to ensure the effectiveness of ensemble learning in co-training as well as to further speed up the learning process, a multi-view semi-supervised feature learning algorithm that expands the single view semi-supervised learning algorithm to multiple views is proposed and embedded in co-training. Finally, a weighted majority vote method is utilized to obtain the classification results. The experimental results for study areas in the United States indicate that the proposed method can accurately map crop types with a limited number of labelled training samples without a significant computational cost.

TIME SERIES LAND COVER CLASSIFICATION BASED ON SEMI-SUPERVISED CONVOLUTIONAL LONG SHORT-TERM MEMORY NEURAL NETWORKS

Abstract. Time series imagery containing high-dimensional temporal features are conducive to improving classification accuracy. With the plenty accumulation of historical images, the inclusion of time series data becomes available to utilize, but it is difficult to avoid missing values caused by cloud cover. Meanwhile, seeking a large amount of training labels for long time series also makes data collection troublesome. In this study, we proposed a semi-supervised convolutional long short-term memory neural network (Semi-LSTM) in long time series which achieves an accurate and automated land cover classification with a small proportion of labels. Three main contributions of this work are summarized as follows: i) the proposed method achieve an excellent classification via a small group of labels in long time series data, and reducing dependence of training labels; ii) it is a robust algorithm in accuracy for the influence of noise, and reduces the requirements of sequential data for cloudless and lossless images; and iii) it makes full advantage of spectral-spatial-temporal features, especially expanding time context information to enhance classification accuracy. Finally, the proposed network is validated on time series imagery from Landsat 8. All quantitative analyses and evaluation indicators of the experimental results demonstrate competitive performance in the suggested modes.

Monitoring the resilience of a no-take marine reserve to a range extending species using benthic imagery.

Global climate change is driving the redistribution of marine species and thereby potentially restructuring endemic communities. Understanding how localised conservation measures such as protection from additional human pressures can confer resilience to ecosystems is therefore an important area of research. Here, we examine the resilience of a no-take marine reserve (NTR) to the establishment of urchin barrens habitat. The barrens habitat is created through overgrazing of kelp by an invading urchin species that is expanding its range within a hotspot of rapid climate change. In our study region, a multi-year monitoring program provides a unique time-series of benthic imagery collected by an Autonomous Underwater Vehicle (AUV) within an NTR and nearby reference areas. We use a Bayesian hierarchical spatio-temporal modelling approach to estimate whether the NTR is associated with reduced formation of urchin barrens, and thereby enhances local resilience. Our approach controls for the important environmental covariates of depth and habitat complexity (quantified as rugosity derived from multibeam sonar mapping), as well as spatial and temporal dependence. We find evidence for the NTR conferring resilience with a strong reserve effect that suggests improved resistance to the establishment of barrens. However, we find a concerning and consistent trajectory of increasing barrens cover in both the reference areas and the NTR, with the odds of barrens increasing by approximately 32% per year. Thus, whereas the reserve is demonstrating resilience to the initial establishment of barrens, there is currently no evidence of recovery once barrens are established. We also find that depth and rugosity covariates derived from multibeam mapping provide useful predictors for barrens occurrence. These results have important management implications as they demonstrate: (i) the importance of monitoring programs to inform adaptive management; (ii) that NTRs provide a potential local conservation management tool under climate change impacts, and (iii) that technologies such as AUVs and multibeam mapping can be harnessed to inform regional decision-making. Continuation of the current monitoring program is required to assess whether the NTR can provide long term protection from a phase shift that replaces kelp with urchin barrens.

The pruning phenological phase-based method for extracting tea plantations by field hyperspectral data and Landsat time series imagery

Tea plantations expansion has occurred in the major tea planting area of Yunnan province, China, however, it is a big challenge to extract and map the distribution of tea plantations due to their non-obvious phenological characteristics in the tropical and subtropical regions. Firstly, we demonstrated the pruning phenological phase of tea plantations by using field hyperspectral data. Secondly, we analyzed the optical features of typical land cover types from the available time series Landsat imagery with the Google Earth Engine (GEE) platform. We proposed a pixel and phenology- based approach to extract and map tea plantations distribution at the 30-m resolution of the historical time period of 2015 to 2019. The resultant map had high user/producer accuracies of 91.07% and 86.90%, respectively. Our study provides a promising new approach to extract and map tea plantations in complex tropical landscapes at fine spatial resolution by using only free historical Landsat imagery.

The urban greenness score: A satellite-based metric for multi-decadal characterization of urban land dynamics

Canada’s urban areas have experienced extensive growth over the past quarter century; however, there has been no consistent, spatially explicit approach for quantifying the loss and gain of greenness in cities nationally. Herein, we developed a novel urban greenness score metric using greenness fractions from a multi-decadal time series (1984–2016) of spectrally unmixed annual Landsat satellite image composites to characterize final year (2016) greenness and its overall change for 18 major Canadian urban areas, summarized by census dissemination area (DA). The applied validation procedure confirmed correlation coefficients (ρ) ranging from 0.67 – 0.85 between reference and estimated greenness fractions, indicating that spectral unmixing is an appropriate method for extracting urban greenness from a time series of medium spatial resolution satellite imagery. Most DAs across Canada sustained a moderate (∼20 % – 40 %) or low (≲ 20 %) level of greenness between 1984 and 2016, but overall there was a decreasing trend in greenness. Eastern urban areas maintained the most greenness over time, while urban areas in the Prairies had the greatest increase in greenness. Densely populated urban areas experienced the greatest loss in greenness (16 % of DAs); whereas, urban areas with a moderately-low density experienced the greatest increase (14 % of DAs). In agreement with previous studies, we found that greenness was negatively associated with urban infilling, with lower greenness levels typically found in urban cores, and greenness loss most often found in the urban periphery in conjunction with urban expansion. Methods presented in this analysis take advantage of the open and longstanding Landsat archive, as well as multiple spatial scales, including sub-pixel unmixing techniques, pixel level greenness faction data summarized for management units, and analysis conducted nationally. The developed urban greenness score provides a comprehensive framework to understand current urban greenness and relate it to its recent past, which supports long-term strategic planning, and can be transferred to other regions across spatial and temporal scales.

GLACIAL LAKE EVOLUTION BASED ON REMOTE SENSING TIME SERIES: A CASE STUDY OF TSHO ROLPA IN NEPAL

Abstract. Himalayan glaciers have retreated rapidly in recent years. Resultant glacial lakes in the region pose potential catastrophic threats to downstream communities, especially under a changing climate. The potential for Glacial Lake Outburst Floods (GLOFs) has increased and studies have assessed the risks of those in Nepal and prioritised several glacial lakes for urgent and closer investigation. The risk posed by the Tsho Rolpa Glacial Lake is one of the most serious in Nepal. To investigate the feasibility of high-frequency monitoring of glacial lake evolution by remote sensing, this paper proposes a workflow for automated glacial lake boundary extraction and evolution using a time series of Sentinel optical imagery. The waterbody is segmented and vectorised using bimodal histograms from water indices. The vectorised lake boundary is validated against reference data extracted from rigorous contemporary unmanned aerial vehicle (UAV)-based photogrammetric survey. Lake boundaries were subsequently extracted at four different epochs to evaluate the evolution of the lake, especially at the glacier terminus. The final lake area was estimated at 1.61 km2, significantly larger than the areal extent last formally reported. A 0.99 m/day maximum, and a 0.45 m/day average, horizontal glacier retreat rates were estimated. The reported research has demonstrated the potential of remote sensing time series to monitor glacial lake evolution, which is particularly important for lakes in remote mountain regions that are otherwise difficult to access.

Using Growing-Season Time Series Coherence for Improved Peatland Mapping: Comparing the Contributions of Sentinel-1 and RADARSAT-2 Coherence in Full and Partial Time Series

Differences in topographic structure, vegetation structure, and surface wetness exist between peatland classes, making active remote sensing techniques such as SAR and LiDAR promising for peatland mapping. As the timing of green-up, senescence, and hydrologic conditions vary differently in peatland classes, and in comparison with upland classes, full growing-season time series SAR imagery was expected to produce higher accuracy classification results than using only a few select SAR images. Both interferometric coherence, amplitude and difference in amplitude time series datasets were assessed, as it was hypothesized that these may be able to capture subtle changes in phenology and hydrology, which in turn differentiate classes throughout a growing season. Groups of variables were compared for their effectiveness in Random Forest classification for both Sentinel-1 and Radarsat-2. The Shapley value was used to determine the contribution of each group of variables in thirty scenarios, and Mean Decrease in Accuracy was compared to evaluate its ability to rank variables by relative importance. Despite being dual-pol, the results of classifications using Sentinel-1 coherence (12-day repeat) were significantly better than using fully polarimetric RADARSAT-2 coherence (24-day repeat), likely owing to the difference in baseline and specific acquisition dates of the data in this study. Overall, full growing season Sentinel-1 coherence time series produced higher accuracy results than fully polarimetric quad pol RADARSAT-2 coherence amplitude, difference in amplitude and polarimetric decomposition time series. Using a full growing season of time-series imagery in classification resulted in higher accuracy than using a few dates over a growing season. Using mean decrease in accuracy to rank and reduce variables resulted in a weaker classification than if the entire time series is used.

Spatiotemporal analysis of trends in vegetation change across an artificial desert oasis, Northwest China, 1975–2010

Vegetation change has become a worldwide environmental concern. Artificial desert oases in the Northwest China are among the most ecologically sensitive environments and are also a repository of ecosystem services by relying on vegetation system. Over the last four decades, land transformation related to anthropogenic activities and climate change is among the main drivers of changing vegetation cover in Northwest China. In an oasis where field-based research is challenging due to diverse landscape and heterogenous relief, quantifying changes in vegetation system using remote sensing can provide available information regarding trends in vegetation cover and its linkages with driving forces. This study aimed to explore spatiotemporal dynamics of vegetation change through examining time series normalized difference vegetation index (NDVI) over the period 1975–2010 in an artificial desert oasis in Northwest China. A time series imagery derived from Landsat product was analyzed for the presence of trends in vegetation change. Using the nonparametric Sen’s and Mann-Kendall methods, over 13.56% of oasis land surfaces were found to exhibit significant increasing trends, and almost 6.07% of oasis land surfaces were found to exhibit significant decreasing trends. The 80.38% spatial distribution of vegetation showed no change trends significantly. The relationships between the detected NDVI trends and land cover also were evaluated by using spatial mapping method. Results showed that the spatiotemporal pattern of vegetation change was consistent with the climate-related change of vegetation growing conditions and implementation of ecosystem management during the study period.

Land use change analysis of Daishan Island using multi-temporal remote sensing imagery

The objective of this paper is to analyze land use change on Daishan Island using a multi-temporal remote sensing imagery. Four Landsat optical remote sensing images were collected from 1987, 1996, 2007, and 2016, and eight land cover types were recognized and extracted using the collected time series imagery. In addition, a land use-type transfer matrix was used for temporal analysis of land use conditions. The experimental results reveal that the total area of Daishan Island increased slightly in the past 30 years, during which time the shipbuilding industry rapidly grew and the salt mining industry gradually shrank. The industry changed greatly but there was no large-scale land reclamation. Moreover, forested area increased, which was conducive to the sustainable development of Daishan Island.

Living with floating vegetation invasions

Invasions of water bodies by floating vegetation, including water hyacinth (Eichhornia crassipes), are a huge global problem for fisheries, hydropower generation, and transportation. We analyzed floating plant coverage on 20 reservoirs across the world’s tropics and subtropics, using > 30 year time-series of LANDSAT remote-sensing imagery. Despite decades of costly weed control, floating invasion severity is increasing. Floating plant coverage correlates with expanding urban land cover in catchments, implicating urban nutrient sources as plausible drivers. Floating vegetation invasions have undeniable societal costs, but also provide benefits. Water hyacinths efficiently absorb nutrients from eutrophic waters, mitigating nutrient pollution problems. When washed up on shores, plants may become compost, increasing soil fertility. The biomass is increasingly used as a renewable biofuel. We propose a more nuanced perspective on these invasions moving away from futile eradication attempts towards an ecosystem management strategy that minimizes negative impacts while integrating potential social and environmental benefits.

A novel method for automatic potato mapping using time series of Sentinel-2 images

Crop maps produced by remote sensing data play an important role in agricultural crop studies. Most of the crop mapping methods rely on field samples to train a model, which is a costly and time-consuming process. On the other hand, automatic crop mapping methods which are based on unique spectral characteristics are independent of ground truth data. Since most crops have specific spectral and temporal features during the growing season, this research aims at developing a new automatic method to discriminate potato from other crops using Sentinel-2 time series imageries. In this research, Crop type data of three study sites in Iran consisting of 2019 fields of potato and other crops, which were sampled by a GPS receiver were used. Moreover, an additional site in the United States comprised of 880 fields from Cropland Data Layer (CDL) in raster format, was also utilized. We employed 50% (292) of the Hamedan fields to train the model and the remaining 2607 fields from other sites and 50% from Hamedan were used to validate the model. Then, the temporal reflectance spectra of various crops and potato were extracted and considered. Results show that potato has four unique spectral characteristics which can be utilized to distinguish potato fields. These include the near-infrared reflectance values at the cultivation and harvest dates, variations of the near-infrared reflectance at the greenness peak time and the ratio of the near-infrared reflectance values to the red reflectance values at the greenness peak. Therefore, a novel feature was proposed based on a combination of the above spectral characteristics for discrimination of potato fields with a kappa coefficient of higher than 0.8 and an overall accuracy of better than 90%, in the four study sites.