Investigations on plant community and micronutrient status of Schirmacher Oasis, East Antarctica have been presented in this paper. The dominant plant communities include moss and lichen. The frequency of species occu...Investigations on plant community and micronutrient status of Schirmacher Oasis, East Antarctica have been presented in this paper. The dominant plant communities include moss and lichen. The frequency of species occurrence and changes in species composition at different location varied. Thirty-four soil samples were ana- lyzed for chemical properties of the soils of Schirmacher Oasis and Nunatak, East Antarctica. The most common plant species growing throughout the areas of Sehirmacher Oasis and Nunataks are： Candelariella tiara （ lichen ） and Bryum pseudotriquetrum （moss）. Large variations were observed among different soil samples in all the nutri- ents and other measured soil chemical parameters. The soils are characterized by a-cidic pH ranging from 4.42 - 6.80. The mean organic carbon content was 0.62 and ranged from 0. 06 - 1.29%. The electrical conductivity in 1 ： 2 soil water ratio ranged from 0.06 - 1.29. The average content of macronutrient cation, which are ammonium acetate extractable was in the order of Ca 〉 K 〉 Na 〉 Mg. The average content of DTPA extractable micronutrient cations was in the order of Fe 〉 Mn 〉 Cu 〉 Zn. Thirty one out of 34 samples contained less than 0.80 ppm DTPA extractable Zn. Correlation studies revealed that content of macronutrient cations significantly and positively correlated to that of chlorides. Electrical conductivity exhibited significant and positive relationship with pH, K, Ca, Mg, Na and chloride content. Sodium （r =0.876 ＊ ＊ ） exhibited highest correlation followed by K （r =0. 831 ＊ ＊ ） with chlo- ride content. The correlation coefficient for chlorides was higher with electrical conductivity （r=0.732＊ ＊ ） than pH （r =0. 513 ＊ ＊ ）. Organic carbon content of the soil was positively correlated with Fe （ r = 0. 442 ＊ ）. The nutrient status did not appear to be a limiting factor in growth of plants. Lichen and moss community structure and composition in the study area were not related with fertility status of soil. Terrestrial mosses are most abundant and luxuriant along the soil habitats near bank of water bodies and the melt water streams.展开更多
Rapid and automated identification of blight disease in potato will help farmers to apply timely remedies to protect their produce.Manual detection of blight disease can be cumbersome and may require trained experts.T...Rapid and automated identification of blight disease in potato will help farmers to apply timely remedies to protect their produce.Manual detection of blight disease can be cumbersome and may require trained experts.To overcome these issues,we present an automated system using the Mask Region-based convolutional neural network(Mask R-CNN)architecture,with residual network as the backbone network for detecting blight disease patches on potato leaves in field conditions.The approach uses transfer learning,which can generate good results even with small datasets.The model was trained on a dataset of 1423 images of potato leaves obtained from fields in different geographical locations and at different times of the day.The images were manually annotated to create over 6200 labeled patches covering diseased and healthy portions of the leaf.The Mask R-CNN model was able to correctly differentiate between the diseased patch on the potato leaf and the similar-looking background soil patches,which can confound the outcome of binary classification.To improve the detection performance,the original RGB dataset was then converted to HSL,HSV,LAB,XYZ,and YCrCb color spaces.A separate model was created for each color space and tested on 417 field-based test images.This yielded 81.4%mean average precision on the LAB model and 56.9%mean average recall on the HSL model,slightly outperforming the original RGB color space model.Manual analysis of the detection performance indicates an overall precision of 98%on leaf images in a field environment containing complex backgrounds.展开更多
文摘Investigations on plant community and micronutrient status of Schirmacher Oasis, East Antarctica have been presented in this paper. The dominant plant communities include moss and lichen. The frequency of species occurrence and changes in species composition at different location varied. Thirty-four soil samples were ana- lyzed for chemical properties of the soils of Schirmacher Oasis and Nunatak, East Antarctica. The most common plant species growing throughout the areas of Sehirmacher Oasis and Nunataks are： Candelariella tiara （ lichen ） and Bryum pseudotriquetrum （moss）. Large variations were observed among different soil samples in all the nutri- ents and other measured soil chemical parameters. The soils are characterized by a-cidic pH ranging from 4.42 - 6.80. The mean organic carbon content was 0.62 and ranged from 0. 06 - 1.29%. The electrical conductivity in 1 ： 2 soil water ratio ranged from 0.06 - 1.29. The average content of macronutrient cation, which are ammonium acetate extractable was in the order of Ca 〉 K 〉 Na 〉 Mg. The average content of DTPA extractable micronutrient cations was in the order of Fe 〉 Mn 〉 Cu 〉 Zn. Thirty one out of 34 samples contained less than 0.80 ppm DTPA extractable Zn. Correlation studies revealed that content of macronutrient cations significantly and positively correlated to that of chlorides. Electrical conductivity exhibited significant and positive relationship with pH, K, Ca, Mg, Na and chloride content. Sodium （r =0.876 ＊ ＊ ） exhibited highest correlation followed by K （r =0. 831 ＊ ＊ ） with chlo- ride content. The correlation coefficient for chlorides was higher with electrical conductivity （r=0.732＊ ＊ ） than pH （r =0. 513 ＊ ＊ ）. Organic carbon content of the soil was positively correlated with Fe （ r = 0. 442 ＊ ）. The nutrient status did not appear to be a limiting factor in growth of plants. Lichen and moss community structure and composition in the study area were not related with fertility status of soil. Terrestrial mosses are most abundant and luxuriant along the soil habitats near bank of water bodies and the melt water streams.
基金the Government of India’s Department of Biotechnology under the FarmerZone™initiative(#BT/IN/Data Reuse/2017-18)the Ramalingaswami Re-entry fellowship(#BT/RLF/Re-entry/44/2016).
文摘Rapid and automated identification of blight disease in potato will help farmers to apply timely remedies to protect their produce.Manual detection of blight disease can be cumbersome and may require trained experts.To overcome these issues,we present an automated system using the Mask Region-based convolutional neural network(Mask R-CNN)architecture,with residual network as the backbone network for detecting blight disease patches on potato leaves in field conditions.The approach uses transfer learning,which can generate good results even with small datasets.The model was trained on a dataset of 1423 images of potato leaves obtained from fields in different geographical locations and at different times of the day.The images were manually annotated to create over 6200 labeled patches covering diseased and healthy portions of the leaf.The Mask R-CNN model was able to correctly differentiate between the diseased patch on the potato leaf and the similar-looking background soil patches,which can confound the outcome of binary classification.To improve the detection performance,the original RGB dataset was then converted to HSL,HSV,LAB,XYZ,and YCrCb color spaces.A separate model was created for each color space and tested on 417 field-based test images.This yielded 81.4%mean average precision on the LAB model and 56.9%mean average recall on the HSL model,slightly outperforming the original RGB color space model.Manual analysis of the detection performance indicates an overall precision of 98%on leaf images in a field environment containing complex backgrounds.
