Impact of temperature on yield and related traits in cotton genotypes

Cotton growth and development is influenced by various uncontrollable environmental conditions. Temperature variations in the field can be created by planting at different dates. The objective of the present study was to evaluate the effect of planting dates and thermal temperatures（growing degree days） on yield of 4 cotton genotypes, viz., CIM-598, CIM-599, CIM-602 and Ali Akbar-703. Plants were subjected to 6 planting dates during 2013 and 2014 in a trial conducted in randomized complete block design with four replications. For boll number, boll weight and seed cotton yield, cotton genotypes exhibited significant differences, CIM-599 produced the highest seed cotton yield of 2 062 kg ha^（–1） on account of maximum boll number and boll weight. The highest seed cotton yield was recorded in planting dates from 15 th April to 1st May whereas early and delayed planting reduced the yield due to less accumulation of heat units. Regression analysis revealed that increase of one unit（15 days） from early to optimum date（15th March to 15 th April） increased yield by 93.58 kg ha^–1. Delay in planting also decreased the seed cotton yield with the same ratio. Thus it is concluded that cotton must be sown from 15 th April to 1st May to have good productivity in this kind of environment.

Evaluation of model generalization for growing plants using conditional learning

This paper aims to solve the lack of generalization of existing semantic segmentation models in the crop and weed segmentation domain.We compare two training mechanisms,classical and adversarial,to understand which scheme works best for a particular encoder-decoder model.We use simple U-Net,SegNet,and DeepLabv3+with ResNet-50 backbone as segmentation networks.The models are trained with cross-entropy loss for classical and PatchGAN loss for adversarial training.By adopting the Conditional Generative Adversarial Network(CGAN)hierarchical settings,we penalize different Generators(G)using PatchGAN Discriminator(D)and L1 loss to generate segmentation output.The generalization is to exhibit fewer failures and perform comparably for growing plants with different data distributions.We utilize the images from four different stages of sugar beet.We divide the data so that the full-grown stage is used for training,whereas earlier stages are entirely dedicated to testing the model.We conclude that U-Net trained in adversarial settings is more robust to changes in the dataset.The adversarially trained U-Net reports 10%overall improvement in the results with mIOU scores of 0.34,0.55,0.75,and 0.85 for four different growth stages.

Herbaceous Cultivation Test of Mulberry in Sichuan Sericultural Area

With Guiteyou 2 as the test mulberry variety, mulberry herbaceous cultivation field was established at the planting densities of 60 000,90 000 and 120 000 plants/hm2, respectively. Hybrid mulberry herbaceous cultivation test was conducted, with Tongxiangqing mulberry field of mid-fist-form at conventional planting density of 4 995 plants/hm2 as the control. The results showed that the leaf yield of herbaceous cultivation mulberry was closely related to the planting density. With the increasing planting density, the leaf yield per plant was decreasing, but the leaf yield per unit area of mulberry field was increasing. The annual leaf yield per unit area in the mulberry field with the average planting density of 120 000 plants/hm2 was 37 560 kg/hm2, 2.14 times of that of the control field. The moisture content of mulberry leaf in herbaceous cultivation field was 4.74% higher than the control; the contents of crude protein, crude fat, crude fiber and crude ash were 1.264%, 0.014%, 0.744% and 0.002%lower than the control, respectively. Comparison of leaf rearing with herbaceous cultivation mulberry and control mulberry showed that there was no significant difference in growth status of silkworm. The cocoon weight, cocoon shell weight, cocoon yield per 10 000 larvae, cocoon filament length and non-broken filament length of Chuanshan × Shushui were 12.81%, 14.29%, 13.85%, 5.95% and 7.68% lower than the control, respectively; but the percentage of common cocoons was 0.16% higher than the control; the cleanness and neatness were 0.2 and 1.25 points higher than the control;the filament size was 0.196 dtex lower than the control. The cocoon weight, cocoon shell weight, cocoon yield per 10 000 larvae, cocoon filament length and non-broken filament length of Jingsong × Haoyue were 11.06%, 10.20%, 11.53%, 9.46% and 9.03% lower than the control, respectively;but the percentage of common cocoons was 1.77% higher than the control; the cleanness and neatness were 0.12 and 2.50 points higher the control;and the filament size was 0.196 dtex lower than the control.

Humble Opinion of Roof Gardens

With the swift development of urban construction in China and the boost in people’s demands for green environments in cities, roof gardens are widely used as a new way of greening. This paper deals chiefly with the functions, building principle, classification and composing elements of roof gardens, an analysis of main ecological factors, loads, and waterproof. It suggests that roof gardens will bring about a comparatively big leap in city greening both quantitatively and qualitatively.