The spatial extent of hydrological and landscape changes across the mountains and prairies of Canada in the Mackenzie and Nelson River basins based on data from a warm-season time window

East of the Continental Divide in the cold interior of Western Canada, the Mackenzie and Nelson River basins have some of the world's most extreme and variable climates, and the warming climate is changing the landscape, vegetation, cryosphere, and hydrology. Available data consist of streamflow records from a large number (395) of natural (unmanaged) gauged basins, where flow may be perennial or temporary, collected either year-round or during only the warm season, for a different series of years between 1910 and 2012. An annual warm-season time window where observations were available across all stations was used to classify (1) streamflow regime and (2) seasonal trend patterns. Streamflow trends were compared to changes in satellite Normalized Difference Indices. Clustering using dynamic time warping, which overcomes differences in streamflow timing due to latitude or elevation, identified 12 regime types. Streamflow regime types exhibit a strong connection to location; there is a strong distinction between mountains and plains and associated with ecozones. Clustering of seasonal trends resulted in six trend patterns that also follow a distinct spatial organization. The trend patterns include one with decreasing streamflow, four with different patterns of increasing streamflow, and one without structure. The spatial patterns of trends in mean, minimum, and maximum of Normalized Difference Indices of water and snow (NDWI and NDSI) were similar to each other but different from Normalized Difference Index of vegetation (NDVI) trends. Regime types, trend patterns, and satellite indices trends each showed spatially coherent patterns separating the Canadian Rockies and other mountain ranges in the west from the poorly defined drainage basins in the east and north. Three specific areas of change were identified: (i) in the mountains and cold taiga-covered subarctic, streamflow and greenness were increasing while wetness and snowcover were decreasing, (ii) in the forested Boreal Plains, particularly in the mountainous west, streamflows and greenness were decreasing but wetness and snowcover were not changing, and (iii) in the semi-arid to sub-humid agricultural Prairies, three patterns of increasing streamflow and an increase in the wetness index were observed. The largest changes in streamflow occurred in the eastern Canadian Prairies.

Mapping the groundwater level and soil moisture of a montane peat bog using UAV monitoring and machine learning

<p>One of the best preconditions for sufficient monitoring of peat bog ecosystems requires a unique collection, processing, and analysis of spatial data to understand peat bog dynamics. Over two seasons, we sampled groundwater level (GWL), and soil moisture (SM) ground truth data at two diverse locations at the Rokytka Peat bog within the Sumava Mountains, Czechia. These data served as reference data and were modeled with a suite of potential variables derived from digital surface models (DSMs), RGB-, multispectral-, and thermal orthoimages, reflecting topo-morphometry, vegetation, and surface temperature information, generated from drone mapping. We applied 34 predictors to feed the Random forest (RF) algorithm. Predictors selection, hyperparameter tuning, and performance assessment were accompanied using Leave-Location-Out (LLO) spatial Cross-Validation (CV) joined with the forward feature selection (FFS) to overcome overfitting. The spatial CV performance statistics unveiled low (R2 = 0.12) to high (R2 = 0.78) model predictions. Predictor importance was used for model interpretation, where the temperature has proved the be a powerful impact on GWL and SM and significant other predictors' contributions such as Normalized Difference Index (NDVI), Normalized Difference Index (NDI), Enhanced Red-Green-Blue Vegetation Index (ERGBVE), Shape Index (SHP), Green Leaf Index (GLI), Brightness Index (BI), Coloration Index (CI), Redness Index (RI), Primary Colours Hue Index (HI), Overall Hue Index (HUE), SAGA Wetness Index (TWI), Plan Curvature (PlnCurv), Topographic Position Index (TPI), and Vector Ruggedness Measure (VRM). Additionally, we estimated the area of applicability (AOA) by presenting maps where the prediction model was certainly applied and where the predictions were highly uncertain because machine learning (ML) models make predictions far beyond sampling locations without sampling data and having no knowledge about these environments. The AOA method is perfectly suited and unique for decision-making about the best sampling strategy, notably for limited data to circumvent this issue. </p>

Evaluation of the nutritional status of corn by vegetation indices via aerial images

ABSTRACT: The objective of this study is to determine the vegetation indices (IV) as a means of identifying the nutritional status of corn, with respect to the soil nitrogen and potassium, using the aerial images received through an RGB camera loaded on an unmanned aerial vehicle. The images were obtained for an experiment of the nitrogen levels (0, 60, 120 and 180 kg ha-1) and potassium levels (0, 50, 100 and 150 kg ha-1), in the random block design, with a factorial scheme of 4 x 4, having three repetitions. Ten leaves were plucked per plot during the flowering phase to assess the total N (NF) and K+ leaf contents. The Pearson’s correlation analysis, as well as the analyses of variance and regression between the IV and the concentrations of N and K2O. NF, K+ and the grain yield, responded only to the soil N levels. A significant correlation was observed for the indices of Red Index, Normalized Difference Index and Visible Atmospherically Resistant Index with the NF, which endorses them as favorable in identifying the nutritional standing of corn, with respect to the N level. Not even a single one of the indices evaluated could detect the nutritional ranking of corn in the context of the potassium level.

Hyperspectral Image Classification Using Feature Relations Map Learning

Recently, deep learning has been reported to be an effective method for improving hyperspectral image classification and convolutional neural networks (CNNs) are, in particular, gaining more and more attention in this field. CNNs provide automatic approaches that can learn more abstract features of hyperspectral images from spectral, spatial, or spectral-spatial domains. However, CNN applications are focused on learning features directly from image data—while the intrinsic relations between original features, which may provide more information for classification, are not fully considered. In order to make full use of the relations between hyperspectral features and to explore more objective features for improving classification accuracy, we proposed feature relations map learning (FRML) in this paper. FRML can automatically enhance the separability of different objects in an image, using a segmented feature relations map (SFRM) that reflects the relations between spectral features through a normalized difference index (NDI), and it can then learn new features from SFRM using a CNN-based feature extractor. Finally, based on these features, a classifier was designed for the classification. With FRML, our experimental results from four popular hyperspectral datasets indicate that the proposed method can achieve more representative and objective features to improve classification accuracy, outperforming classifications using the comparative methods.

Assessment of Wheat Straw Cover and Yield Performance in a Rice-Wheat Cropping System by Using Landsat Satellite Data

Proper straw cover information is one of the most important inputs for agroecosystem and environmental modeling, but the availability of accurate information remains limited. However, several remote-sensing (RS)-based studies have provided a residue cover estimation and provided spatial distribution mapping of paddy rice areas in a constant field condition. Despite this, the performance of rice crops with straw applications has received little attention. Furthermore, there are no methods currently available to quantify the wheat straw cover (WSC) percentage and its effect on rice crops in the rice-wheat cropping region on a large scale and a continuous basis. The novel approach proposed in this study demonstrates that the Landsat satellite data and seven RS-based indices, e.g., (i) normalized difference vegetation index (NDVI), (ii) Normalized difference senescent vegetation index (NDSVI), (iii) Normalized difference index 5 (NDI5), (iv) Normalized difference index 7 (NDI7), (v) Simple tillage index (STI), (vi) Normalized difference tillage index (NDTI), and (vii) Shortwave red normalized difference index (SRNDI), can be used to estimate the WSC percentage and determine the performance of rice crops over the study area in Changshu county, China. The regression model shows that the NDTI index performed better in differentiating the WSC at sampling points with a coefficient of determination (R2 = 0.80) and root mean squared difference (RMSD = 8.46%) compared to that of other indices, whereas the overall accuracy for mapping WSC was observed to be 84.61% and the kappa coefficient was κ = 0.76. Moreover, the rice yield model was established by correlating between the peak NDVI values and rice grain yield collected from ground census data, with R2 = 0.85. The finding also revealed that the highest estimated yield (8439.67 kg/ha) was recorded with 68% WCS in the study region. This study confirmed that the NDVI and NDTI algorithms are very effective and robust indicators. Also, it can be strongly concluded that multispectral Landsat satellite imagery is capable of measuring the WSC percentage and successively determines the impact of different WSC percentages on rice crop yield within fields or across large regions through remote sensing (RS) and geographical information system (GIS) techniques for the long-term planning of agriculture sustainability in rice-wheat cropping systems.

The Interannual Calibration and Global Nighttime Light Fluctuation Assessment Based on Pixel-Level Linear Regression Analysis

The Operational Linescan System (OLS) carried by the National Defense Meteorological Satellite Program (DMSP) can capture the weak visible radiation emitted from earth at night and produce a series of annual cloudless nighttime light (NTL) images, effectively supporting multi-scale, long-term human activities and urbanization process research. However, the interannual instability and sensor bias of NTL time series products greatly limit further studies of lighting data in time series with OLS. Several calibration models for OLS have been proposed to implement interannual corrections to improve the continuity and consistency of time series NTL products; however, due to the subjective factors intervention and insufficient automation in the calibration process, the interannual correction study of NTL time series images is still worth being developed further. Therefore, to avoid the involvement of subjective factors and to optimize the Pseudo-Invariant Features (PIF) identification, an interannual calibration model Pixel-based PIF (PBPIF) is proposed, which identifies PIF by pixel fluctuation characteristics. Results show that a PBPIF-based model can reduce subjective interference and improve the degree of automation during the NTL interannual calibration process. The calibration performance evaluation based on Total Sum of Lights (TSOL) and Sum of the Normalized Difference Index (SNDI) shows that compared to the traditional PIF-based (tPIF-based) and Ridgeline Sampling Regression based (RSR-based) models, the PBPIF-based one achieves better performance in reducing NTL interannual turbulence and minimizing the deviation between sensors. In addition, based on the corrected NTL time series products, pixel-level linear regression analysis is implemented to maximize the potential of the NTL resolution to produce global Light Intensity Change Coefficient (LICC). The results of global LICC can be widely applied to the detailed study of the characteristics of economic development and urbanization.

Model to Estimate Soil Erosion Based on Imaging Analysis

The study aimed to development a prediction model for soil erosion degree by image analysis techniques. The spectral information was obtained by image analysis in the RGB and HSB color system, and by calculus resulted rgb normalized values. Specific indices were calculated: intensity (INT), normalized difference index (NDI) and dark green color index (DGCI). The correlation analysis emphasized the existence of high levels of interdependence between specific indices and normalized color data rgb, respectively luminance (L). The regression analysis has enabled the creation of estimation models for soil erosion degree (DSE), in the form of linear equations in relation to luminance (R2=0.999, p<<0.001, RMSEP=25.5766) and INT (R2=0.998, p<<0.001, RMSEP=25.5833), and 2nd degree polynomial equations in relation to DGCI (R2=0.768, p<0.001, RMSEP=28.3275). Clustering analysis facilitated the grouping of the studied cases in two distinct clusters with four sub-clusters, under conditions of statistical accuracy, Coph. corr. = 0.831.

Mapping Foliar Nutrition Using WorldView-3 and WorldView-2 to Assess Koala Habitat Suitability

Conservation planning and population assessment for widely-distributed, but vulnerable, arboreal folivore species demands cost-effective mapping of habitat suitability over large areas. This study tested whether multispectral data from WorldView-3 could be used to estimate and map foliar digestible nitrogen (DigN), a nutritional measure superior to total nitrogen for tannin-rich foliage for the koala (Phascolarctos cinereus). We acquired two WorldView-3 images (November 2015) and collected leaf samples from Eucalyptus woodlands in semi-arid eastern Australia. Linear regression indicated the normalized difference index using bands “Coastal” and “NIR1” best estimated DigN concentration (% dry matter, R2 = 0.70, RMSE = 0.19%). Foliar DigN concentration was mapped for multi-species Eucalyptus open woodlands across two landscapes using this index. This mapping method was tested on a WorldView-2 image (October 2012) with associated koala tracking data (August 2010 to November 2011) from a different landscape of the study region. Quantile regression showed significant positive relationship between estimated DigN and occurrence of koalas at 0.999 quantile (R2 = 0.63). This study reports the first attempt to use a multispectral satellite-derived spectral index for mapping foliar DigN at a landscape-scale (100s km2). The mapping method can potentially be incorporated in mapping and monitoring koala habitat suitability for conservation management.

Estimación del Cambio de Volumen del Glaciar Champará en la Cordillera Blanca de Ancash a Partir de Datos de Satélite en el Periodo 2000-2010

Estimación del Cambio de Volumen del Glaciar Champará en la Cordillera Blanca de Ancash a Partir de Datos de Satélite en el Periodo 2000-2010 Juvenal Tordocillo Puchuc, Joel Rojas Acuña Universidad Nacional del Callao, Av. Juan Pablo II s/n Callao 2, Perú. Universidad Nacional Mayor de San Marcos, Ap. Postal 14-0149. Lima, Perú. DOI: https://doi.org/10.33017/RevECIPeru2012.0008/ RESUMEN Se ha estimado, el cambio de área y volumen glaciar empleando las herramientas de la teledetección, basado en el procesamiento e interpretación de las imágenes adquiridas de los sensor ASTER a bordo del satélite TERRA, siendo el área de estudio el Glaciar Champará, el periodo de estudio comprende de 2000 -2010. La metodología utilizada para la estimación del área superficial del glaciar se utilizó el Índice de Diferencia Normalizada de la Nieve (NDSI) y el Índice de Diferencia Normalizada del Agua (NDWI), que sirve para eliminar agua pro glaciar que inicialmente se considera como glaciar. En base a ésta metodología se observa, una variación paulatina del área del Glaciar Champará, el cual muestra una reducción del 64% desde 1975 a la actualidad. La tasa de cambio promedio para el periodo 2000-2010 es de 1.03km2 /año. La variación del cambio del volumen del glaciar para el periodo 2000-2010 del Glaciar Champará se determinó a partir de las ecuaciones empíricas propuestos por BARTH y MEIER, (1997) y los modelos de elevación digital generados de las imágenes ASTER de las bandas 3N y 3B. Descriptores: Flujo Glaciar, Teledetección, Sensor ASTER, LANDSAT 5 TM, Glaciar Champará. ABSTRACT It has been estimated, the change in glacier area and volume using remote sensing tools, based on the processing and interpretation of images acquired from the ASTER sensor aboard the Terra satellite, being, the study area the glacier Champará, the studio period covers 2000 to 2010. The methodology used to estimate the glacier's surface area was used Normalized Difference Index of Snow (NDSI) and the Index Normalized Difference Water (NDWI), which serves to remove water that initially pro glacier ice is considered. Based on this methodology can be seen, a gradual variation of the Glacier area Champará, which shows a 64% reduction from 1975 to present. The average exchange rate for the period 2000-2010 is 1.03km2/año. The variation of the volume of the glacier for the period 2000-2010 the glacier Champará was determined from the empirical equations proposed by BARTH and MEIER, (1997) and digital elevation models generated from the ASTER image of the bands 3N and 3B. Keywords: Glacier flow, Remote Sensing, Sensor ASTER, LANDSAT 5 TM, Glacier Champará.