saeedkhaki92 / cnn-rnn-yield-prediction Goto Github PK

Hello,

My name is Mehathab, I am an aspiring Data Scientist,
I have gone through your paper and found it very interesting,
I have made a new model using LSTM, GRU and CNN for the dataset, but now cannot understand how do we predict the future yield without the future x_train values?

also what is the sequencing you are using for the dataset creating,
what i am doing is,
my model will consider the last 10 data points for predicting yield,

Code i am using is :

def split_sequences(sequences, n_steps_in, n_steps_out):
    X, y = list(), list()
    for i in range(len(sequences)):
        # find the end of this pattern
        end_ix = i + n_steps_in
        out_end_ix = end_ix + n_steps_out - 1
        # check if we are beyond the dataset
        if out_end_ix > len(sequences):
            break
        # gather input and output parts of the pattern
        seq_x, seq_y = sequences[i:end_ix, 1:], sequences[end_ix - 1:out_end_ix, 0]
        X.append(seq_x)
        y.append(seq_y)
    return np.array(X), np.array(y)

where n_steps_in = 10, n_step_out = 5

since i am a new to Forecasting problems,
can you help me with this ?
is this correct?

Batch_X_e = out_tr[:, :, 3:-1].reshape(-1,652+100+16+4)Batch_X_e = out_tr[:, :, 3:-1].reshape(-1,652+100+16+4)
je suis entrain de reprendre les codes
et j'aimerai savoir si cette ligne de codes permet de reformer le tenseur en forme (16,10,1)?

Hi!!! Thank you so much for sharing this! I was seeing your data has a discrepancy of the soil data of being 11 variables x 6 depths but in the code is expected 100 variables for soil (+4 extra) is there a reason for this?

Thank you!!!

I get ValueError: could not broadcast input array from shape (396) into shape (434) when running the codes.

This is the stacktrace:

Traceback (most recent call last): File "CNN_RNN_soybean.py", line 703, in <module> rmse_tr,rmse_te,train_loss,validation_loss=main_program(X, Index,num_units,num_layers,Max_it, learning_rate, batch_size_tr,le,l) File "CNN_RNN_soybean.py", line 520, in main_program out_tr = get_sample(dic, A, avg,batch_size_tr, time_steps=5, num_features=316+100+14+4) File "CNN_RNN_soybean.py", line 317, in get_sample out[i, j, :] = np.concatenate((X[r2, :],np.array([[ym]])),axis=1) ValueError: could not broadcast input array from shape (396) into shape (434)

I read your paper on predicting crop yield using CNNs& RNNs using weather,soil and management features to predict crop yield, the paper is quite beautifully written and goes over all aspects of the project making it a really good read. The approach is quite different and interesting.
I am a Biological Engineering student and I am working on using Machine Learning and Deep Learning in the biological domain especially Agriculture. So I am writing this mail to enquire about the possibility of sharing the dataset for my Thesis Project. I am thinking of performing experiments using the current state of the art approaches such as Transformers and in ML domain GBMS,LGBMs and using Complex Imputing techniques such as Iterative Imputer,KNN imputer,Deep Learning based imputations. Therefore, this dataset would hugely benefit my research. I will duly cite the authors in my work. Looking forward to hearing from you.

I found something wrong with your dataset during debugging. Could you please upload the original dataset corresponding to the code? Thank you very much！

Thank you for your effort in creating the dataset. Can you please provide the official lincense under which the provided datasets fall under?

When I run the code I get the following message:

AttributeError: module 'tensorflow' has no attribute 'placeholder'

Could you please provide the file DATA_corn?