Crop type discrimination using Geo-Stat Endmember Extraction and machine learning algorithms.

The identification of crop diversity in today's world is very crucial to ensure adaptation of the crop with changing climate for better productivity as well as food security. Towards this, Hyperspectral Remote Sensing (HRS) is an efficient technique based on imaging spectroscopy that offers the opportunity to discriminate crop types based on morphological as well as physiological features due to availability of contiguous spectral bands. The current work utilized the benefits of Airborne Visible Infrared Imaging spectrometer- New Generation (AVIRIS-NG) data and explored the techniques for classification and identification of crop types. The endmembers were identified using the Geo-Stat Endmember Extraction (GSEE) algorithm for pure pixels identification and to generate the spectral library of the different crop types. Spectral feature comparison was done among AVIRIS-NG, Analytical Spectral Device (ASD)-Spectroradiometer and Continuum Removed (CR) spectra. The best-fit spectra obtained with the Reference ASD-Spectroradiometer and Pure Pixel spectral library were then used for crop discrimination using the ten supervised classifiers namely Spectral Angle Mapper (SAM), Spectral Information Divergence (SID), Support Vector Machine (SVM), Minimum Distance Classifier (MDC), Binary Encoding, deep learning-based Convolution Neural Network (CNN) and different algorithms of Ensemble learning such as Tree Bag, AdaBoost (Adaptive Boosting), Discriminant and RUSBoost (Random Under Sampling). In total, nine crop types were identified, namely, wheat, maize, tobacco, sorghum, linseed, castor, pigeon pea, fennel and chickpea. The performance evaluation of the classifiers was made using various metrics like Overall Accuracy, Kappa Coefficient, Precision, Recall and F1 score. The classifier 2D-CNN was found to be the best with Overall Accuracy, Kappa Coefficient, Precision, Recall and F1 score values of 89.065 %, 0.871,87.565%, 89.541% and 88.678% respectively. The output of this work can be utilized for large scale mapping of crop types at the species level in a short interval of time of a large area with high accuracy.

Vegetation health conditions assessment and mapping using AVIRIS-NG hyperspectral and field spectroscopy data for -environmental impact assessment in coal mining sites.

This paper focuses on vegetation health conditions (VHC) assessment and mapping using high resolution airborne hyperspectral AVIRIS-NG imagery and validated with field spectroscopy-based vegetation spectral data. It also quantified the effect of mining on vegetation health for geo-environmental impact assessment at a fine level scale. In this study, we have developed and modified vegetation indices (VIs) based model for VHC assessment and mapping in coal mining sites. We have used thirty narrow banded VIs based on the statistical measurement for suitable VIs identification. The highest Pearson's r, R2, lowest RMSE, and P values indices have been used for VIs combined pixels analysis. The highest different (Healthy vs. unhealthy) vegetation combination index (VCI) has been selected for VHC assessment and mapping. We have also compared VIs model-based VHC results to ENVI (software) forest health tool and Spectral-based SAM classification results. The 1st VCI result showed the highest difference (72.07%) from other VCI. The AUC values of the ROC curve have shown a better fit for the VIs model (0.79) than Spectral classification (0.74), and ENVI FHT (0.68) based on VHC results. The VHC results showed that unhealthy vegetation classes are located at low distances from mine sites, and healthy vegetation classes are situated at high distances. It is also seen that there is a highly significant positive relationship (R2 =0.70) between VHC classes and distance from mines. These results will provide a guideline for geo-environmental impact assessment in coal mining sites.

Phenocam observed flowering anomaly of Rhododendron arboreum Sm. in Himalaya: a climate change impact perspective.

Flowering exhibits a significant relationship with environmental stimuli and changes. Effect of photoperiodism and vernalization have been well studied in flowering phenology; however, the effect of soil temperature on flowering is less explored which is one of the major factors of vegetation growth in alpine ecosystem. This study thus focuses on the effects of soil and air temperature on flowering response of Rhododendron arboreum Sm., a Himalayan tree species, which is also an indicator of spring initiation in high altitude regions. To monitor the flowering pattern, we employed automated phenocam, which was set up at 3356 masl in Tungnath (Indian Alpine region of Uttarakhand) for time-lapse photography of timberline ecotone. Soil and air temperature were recorded continuously at the timberline ecotone. Three years (2017 to 2020) of datasets were used for the present study. The phenocam observations displayed an interesting event in the year 2019-2020 with complete absence of flowering in R. arboreum population at Tungnath timberline ecotone. From the soil temperature data, an increase in winter (Dec-Jan, during which floral buds form) soil temperature, by > 1 °C, and no accumulation of freezing degree-days were found for the year 2019-2020. Air temperature however did not display any relationship with the failure of flowering, ruling out aerial chilling or frost injury of floral buds. From the results, a possible relationship between soil temperature and flowering can be suggested pointing towards necessary root apex vernalization stimulus in shallow rooted Rhododendrons. However, the dependency of flowering in Rhododendrons on winter soil temperature further requires continuous monitoring and more observations to make concrete inferences.

Denoising AVIRIS-NG Data for Generation of New Chlorophyll Indices.

The availability of Airborne Visible and Infrared Imaging Spectrometer-Next Generation (AVIRIS-NG) data has enormous possibilities for quantification of Leaf Chlorophyll Content (LCC). The present study used the AVIRIS-NG campaign site of Western India for generation and validation of new chlorophyll indices by denoising the AVIRIS-NG data. For validation, concurrent to AVIRIS-NG flight overpass, field samplings were performed. The acquired AVIRIS-NG was subjected to Spectral Angle Mapper (SAM) classifier for discriminating the crop types. Three smoothing techniques i.e., Fast-Fourier Transform (FFT), Mean and Savitzky-Golay filters were evaluated for their denoising capability. Raw and filtered data was used for developing new chlorophyll indices by optimizing AVIRIS-NG bands using VIs based on parametric regression algorithms. In total, 20 chlorophyll indices and corresponding 20 models were developed for mapping LCC in the area. SAM identified 17 crop types in the area, while FFT found to be the best for filtering. Performance of these models when checked based on Pearson correlation coefficient (r) and Centered Root Mean Square Difference (CRMSD), indicated that LCC-CCI10 based on normalized difference type index formed through Near Infrared band and blue band is the best estimator of LCC (rcal = 0.73, rval = 0.66, CRMSD = 4.97). The approach was also tested using AVIRIS-NG image of the year 2018, which also showed a promising correlation (r = 0.704, CRSMD = 8.98, Bias = -0.5) between modeled and field LCC.

Agricultural drought early warning from geostationary meteorological satellites: concept and demonstration over semi-arid tract in India.

Remote sensing data from Indian geostationary satellites (Kalapana-1, INSAT 3A) were used for the first time for early warning of agricultural drought and forewarning of crop vigour. An Early warning indicator (EWI) was developed from operational product of rainfall and reference evapotranspiration from observations of Kalpana-1 very high resolution radiometer (VHRR). The effectiveness of EWI was evaluated for the two drought years (2009 and 2012). The positive correlation (r = 0.66-0.68 for 2009 and r = 0.64-0.70 for 2012) between the EWI in the month of June-July and standardized precipitation index-1 (SPI-1) averaged over administrative unit (called district) indicates that EWI can be used successfully for drought early warning. Lag-response behaviour between EWI and crop vigour in terms of normalized difference vegetation index (NDVI) and LAI (leaf area index) over cropland was studied. Systematic patterns emerged for 30 days lag period between negative EWI and NDVI at both grid-scale (0.25°) and at district level. Linear relations were found between 10-day EWI and NDVI or LAI at 30 days lag during June-July period. Linear models were developed to forewarn crop vigour which was validated with realized NDVI from INSAT 3A charge-coupled device (CCD) observations within 95% accuracy. The EWI is recommended as potential indicator for early-season agricultural drought assessment and can be used for sub-district scale with finer scale rainfall and evaporation products from advanced next-generation geostationary meteorological satellites.

New findings on impact of COVID lockdown over terrestrial ecosystems from LEO-GEO satellites.

The COVID 19 pandemic led to lockdown and restrictions on anthropogenic activities not only in India but all over the world. This provided an opportunity to study positive effects on environment and subsequent impact on terrestrial ecosystems such as urban, peri-urban, forest and agriculture. A variety of studies presented so far mainly include improved air quality index, water quality, reduced pollutants etc. The present study focused on few novel parameters from both polar and geostationary satellites that are not studied in context to India, and also attempts deriving/quantifying benefits rather than merely indicating qualitative improvements. Due to lack of anthropogenic activities during complete lockdown-1 (21 days from 25 March 2020) in India nighttime cooling of land surface temperature (LST) of the order of 2-6 K was observed. Amongst 10 major cities, Bhopal showed highest nighttime cooling. The cooling effect in LST was evident in 80% of industrial units distinctly indicating cooling trend. Vegetation fires were analyzed in 10 fire-prone states of India. Compared to past four-years average number of occurrences, only 45% fire occurrences occurred during lockdown, indicating strong effect of lockdown. The study also revealed that, there is increase in gross primary production in forest ecosystem to the tune of maximum 38%, during this period. Though delay in rabi crop harvest date by 1-2 weeks in majority of north Indian states was observed rise in rabi crop productivity of the order of maximum 34% was observed which is attributed to favorable environmental conditions for net carbon uptake. About 18% reduction in volumetric agricultural water demand was estimated in Indo-Gangetic region, parts of Gujarat and Rajasthan. Apart from controlling the spread of the disease, the lockdown restrictions were thus also able to show positive effects on the environment and ecosystem which might influence to rethink on strategies for sustainable development.